> ## Documentation Index
> Fetch the complete documentation index at: https://opensre.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Interactive Shell Privacy

> How OpenSRE redacts secrets from command history and LLM prompt/response logs, and the controls you have over persistence and cloud telemetry.

## Overview

The interactive shell saves every line you type to a history file so up-arrow
recall and `/history` work across sessions. Each new prompt reloads the file
when another running shell has changed it, so concurrent sessions share recent
commands without a restart. Separately, it records each LLM prompt/response turn
for local debugging and `/resume`. Incident prompts can include sensitive
identifiers and tokens, so the shell:

* Redacts known token shapes before each entry is written to disk
* Supports disabling persistence entirely (memory-only mode)
* Caps how many entries are kept (oldest pruned)
* Offers `/history clear` to wipe the file on demand

The history file is `~/.opensre/interactive_history`. See
[Prompt and response logging](#prompt-and-response-logging) for the separate LLM
turn log and remote product-analytics forwarding.

## Defaults

| Setting       | Default          | Effect                                                                   |
| ------------- | ---------------- | ------------------------------------------------------------------------ |
| Persistence   | **on**           | Lines you type are appended to the history file.                         |
| Redaction     | **on**           | Known token shapes are replaced with `[REDACTED:<kind>]` before writing. |
| Retention cap | **5000 entries** | Older entries are pruned when the cap is exceeded.                       |

## Redaction patterns

The built-in patterns target token shapes that are distinctive enough to keep
false positives on natural-language incident text low. Each match becomes a
labeled placeholder.

| Kind            | Examples                     |
| --------------- | ---------------------------- |
| `aws_key`       | `AKIA…`, `ASIA…`             |
| `aws_secret`    | `aws_secret_access_key=…`    |
| `github_pat`    | `ghp_…`, `github_pat_…`      |
| `anthropic_key` | `sk-ant-…`                   |
| `openai_key`    | `sk-…`                       |
| `slack_token`   | `xoxb-…`, `xoxp-…`, `xoxa-…` |
| `stripe_key`    | `sk_live_…`, `sk_test_…`     |
| `bearer`        | `Bearer <opaque>` headers    |
| `jwt`           | `eyJ…` three-segment tokens  |
| `password`      | `--password=…`, `password=…` |
| `private_key`   | PEM-encoded private keys     |

Redaction applies only to **persistent history**. The line you typed is still
passed to OpenSRE’s normal pipeline as you typed it.

## Slash commands

| Command                  | Effect                                                                         |
| ------------------------ | ------------------------------------------------------------------------------ |
| `/history`               | Show all persisted entries.                                                    |
| `/history clear`         | Wipe the history file. Up-arrow recall resets on next launch.                  |
| `/history off`           | Pause persistence for this session. New entries are not written.               |
| `/history on`            | Resume persistence for this session.                                           |
| `/history retention <N>` | Keep at most N entries on disk. Prunes immediately.                            |
| `/privacy`               | Show current persistence and redaction state, retention cap, and threat model. |

## Configuration

Settings resolve from (highest wins):

1. Environment variables
2. The `interactive.history` block in `~/.opensre/config.yml`
3. Built-in defaults

### Environment variables

| Variable                      | Default | Effect                                                                      |
| ----------------------------- | ------- | --------------------------------------------------------------------------- |
| `OPENSRE_HISTORY_ENABLED`     | `1`     | Set to `0` / `false` / `off` to skip persistence entirely (in-memory only). |
| `OPENSRE_HISTORY_REDACT`      | `1`     | Set to `0` / `false` / `off` to disable redaction (raw `FileHistory`).      |
| `OPENSRE_HISTORY_MAX_ENTRIES` | `5000`  | Non-negative integer. `0` disables the cap (unlimited).                     |

### Config file

```yaml theme={null}
interactive:
  history:
    enabled: true
    redact: true
    max_entries: 5000
```

## Prompt and response logging

Separately from typed-command history, OpenSRE records each agent turn — the
submitted prompt and final response — in the interactive shell,
`opensre ask`, gateway chat, and scheduled or embedded agent runs. Failures and
cancellations retain the prompt and available error details. Each continuation
is recorded separately. This log is richer than command history (it includes model
output, not just what you typed) and is used for two purposes:

1. **Local debugging / `/resume`**: appended as JSON Lines to
   `~/.opensre/prompt_log.jsonl`, and folded into the session file so `/resume`
   can restore conversation context. Gateway logs use the organization and user
   conversation directory rather than the host-wide default. An explicit
   `OPENSRE_PROMPT_LOG_PATH` overrides that location.
2. **Product analytics**: forwarded through the first-party OpenSRE app endpoint
   as an `$ai_generation` event
   (model, provider, latency, token counts, and the prompt/response text) so
   usage and quality can be tracked. Failed turns carry structured error properties (`$ai_is_error`,
   `$ai_error`, `error_kind`). Turns handled entirely by terminal tools or slash
   commands report `$ai_model` / `$ai_provider` as `no_conversational_agent`;
   when a conversational reply was intended but the LLM provider failed (missing
   API key, model access, quota, auth), the event reports the attempted model
   (or `unknown`) plus an `ai_error_kind` bucket (`not_configured`, `quota`,
   `auth`, or `provider_error`).

### Defaults

| Setting           | Default | Effect                                                                                                              |
| ----------------- | ------- | ------------------------------------------------------------------------------------------------------------------- |
| Logging           | **on**  | Each LLM turn is recorded.                                                                                          |
| Local JSONL file  | **on**  | Turns are appended to `~/.opensre/prompt_log.jsonl`.                                                                |
| Remote forwarding | **on**  | Turns are also sent as a product-analytics `$ai_generation` event.                                                  |
| Redaction         | **on**  | Known token shapes (same patterns as command history) are stripped from the prompt and response before either sink. |

### Environment variables

| Variable                            | Default                       | Effect                                                                                           |
| ----------------------------------- | ----------------------------- | ------------------------------------------------------------------------------------------------ |
| `OPENSRE_PROMPT_LOG_DISABLED`       | `0`                           | Set to `1` to disable prompt/response logging entirely (both local file and remote analytics).   |
| `OPENSRE_PROMPT_LOG_LOCAL_DISABLED` | `0`                           | Set to `1` to skip the local JSONL file while leaving remote forwarding (if enabled) unaffected. |
| `OPENSRE_PROMPT_LOG_REDACT`         | `1`                           | Set to `0` to log/send raw prompt and response text without redaction.                           |
| `OPENSRE_PROMPT_LOG_PATH`           | `~/.opensre/prompt_log.jsonl` | Override the local JSONL file path.                                                              |

The separate operations log at `~/.opensre/operations_log.jsonl` records agent
and scheduler lifecycle breadcrumbs such as loop start, iteration outcome, loop
creation, and delivery status. It does not store prompt or response bodies.

Remote forwarding for this event also honors the global telemetry opt-outs: set
**`OPENSRE_NO_TELEMETRY=1`**, `OPENSRE_ANALYTICS_DISABLED=1`, or `DO_NOT_TRACK=1`
to stop all product analytics (including `$ai_generation`) without touching the
local JSONL file. See
[Environment variables](/docs/install/environment-variables#telemetry-monitoring).

### Config file

```yaml theme={null}
interactive:
  prompt_log:
    posthog_enabled: true
    redact: true
    max_chars: 32000
    path: ~/.opensre/prompt_log.jsonl
```

Redaction here uses the same built-in pattern set as command history (see
[Redaction patterns](#redaction-patterns) above). It catches known secret
shapes, not arbitrary sensitive content. Raw incident details, hostnames, or
business context in a prompt are not redacted — only credential-shaped
substrings.

## Threat model

The history file is **plain text on local disk** at
`~/.opensre/interactive_history`, with the user’s default file permissions.
Built-in redaction targets common token shapes only — it is not a substitute for
proper secret handling. Treat the file as confidential and be aware:

* A determined attacker with read access to your home directory can still read
  entries written before redaction was enabled.
* Redaction cannot detect tokens that look like normal text (for example a
  natural-language password). Do not paste secrets you would not put in a system
  log.
* Custom redaction patterns are not supported in v1. To redact internal token
  shapes, use `/history off` for that session and run `/history clear`
  afterwards.

The prompt/response log has the same caveats, plus one more: with remote
forwarding on (the default), redacted prompt/response text leaves your machine.
If you discuss confidential systems or data in the interactive shell, set
`OPENSRE_NO_TELEMETRY=1` (or `OPENSRE_PROMPT_LOG_DISABLED=1` to also stop the
local file) rather than relying on redaction alone.

For a strong local posture: set `OPENSRE_HISTORY_ENABLED=0` and
`OPENSRE_NO_TELEMETRY=1`. That stops command-history persistence and remote analytics.
Up-arrow recall across sessions is lost. `/resume` conversation context also
depends on session files and the prompt log — set
`OPENSRE_PROMPT_LOG_DISABLED=1` (or clear session/prompt-log data) if you need
that path off too. Otherwise rely on the in-memory ring for the current process.