> For the complete documentation index, see [llms.txt](https://docs.interactive.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.interactive.ai/agents/reference/limits-and-defaults.md).

# Limits & defaults

Every default and cap in one table: manifest field defaults, operator env-var defaults, hardcoded model defaults, and behavioural constants.

> **Context** — Every default value and cap in one place, introspected from runtime version `1.4.0` (manifest schema 1.4.0). Field semantics live on the concept pages; this is the lookup table.

## Manifest field defaults

| Field                                                     | Default                                      |
| --------------------------------------------------------- | -------------------------------------------- |
| `agent_config.runtime.log_level`                          | `"INFO"`                                     |
| `agent_config.runtime.max_engine_iterations`              | `5`                                          |
| `agent_config.runtime.policy_batch_size`                  | `5`                                          |
| `agent_config.runtime.streaming`                          | `false`                                      |
| `agent_config.runtime.startup_review`                     | `true`                                       |
| `agent_config.runtime.generation_attempts`                | `3`                                          |
| `agent_config.runtime.autonomous_default_timeout_seconds` | `120`                                        |
| `agent_config.runtime.autonomous_max_timeout_seconds`     | `600`                                        |
| `agent_config.runtime.autonomous_callback_max_retries`    | `5`                                          |
| `agent_config.runtime.run_retention_days`                 | `30`                                         |
| `agent_config.runtime.turn_recording`                     | `true`                                       |
| `agent_config.llms.default`                               | `"interactive/openai/gpt-6-luna"`            |
| `agent_config.llms.fallback`                              | `["interactive/anthropic/claude-haiku-5.5"]` |
| `agent_config.database.port`                              | `5432`                                       |
| `agent_config.database.user`                              | `"postgres"`                                 |
| `agent_config.database.dbname`                            | `"postgres"`                                 |
| `agent_config.database.sslmode`                           | `"require"`                                  |
| `agent_config.search (external).type`                     | `"external"`                                 |
| `agent_config.search (external).top_k`                    | `5`                                          |
| `agent_config.search (external).max_messages`             | `20`                                         |
| `agent_config.search (external).timeout_seconds`          | `5.0`                                        |
| `agent_config.search (collections).type`                  | `"collections"`                              |
| `agent_config.search (collections).operator_base_url`     | `"https://deployment.interactive.ai"`        |
| `agent_config.search (collections).limit`                 | `5`                                          |
| `agent_config.search (collections).history_limit`         | `5`                                          |
| `agent_config.search (collections).filter`                | `{}`                                         |
| `agent_config.search (collections).fusion_k`              | `60`                                         |
| `agent_config.search (collections).exact`                 | `false`                                      |
| `agent_config.traces.deployment_environment`              | `"production"`                               |
| `agent_config.traces.backend.api_key_scheme`              | `"bearer"`                                   |
| `agent_config.webhooks[].algorithm`                       | `"sha256"`                                   |
| `agent_config.webhooks[].prefix`                          | `""`                                         |

## Operator env-var defaults

| Variable                         | Default  |
| -------------------------------- | -------- |
| `ROUTER_MAX_TOKENS`              | `100000` |
| `SHUTDOWN_DRAIN_TIMEOUT_SECONDS` | `120`    |
| `LLM_PROVIDER_ORDER`             | unset    |
| `AGENT_NAME`                     | unset    |
| `AGENT_REVISION`                 | unset    |

## Hardcoded model defaults

| Slot                                                      | Default                                  |
| --------------------------------------------------------- | ---------------------------------------- |
| Customer-facing (`llms.default` absent)                   | `interactive/openai/gpt-6-luna`          |
| Customer-facing fallback models (`llms.fallback` absent)  | `interactive/anthropic/claude-haiku-5.5` |
| Evaluation (`llms.evaluation.default` absent)             | `interactive/openai/gpt-6-luna`          |
| Evaluation escalation (`llms.evaluation.fallback` absent) | `interactive/anthropic/claude-haiku-5.5` |

## Behavioural constants

| Constant                     | Value                   | Meaning                                                                                                         |
| ---------------------------- | ----------------------- | --------------------------------------------------------------------------------------------------------------- |
| HTTP port                    | `8080`                  | Container listen port.                                                                                          |
| Reply attempt limit          | `180s`                  | One attempt at writing the reply; a model still silent at this point counts as a failed attempt, like an error. |
| Evaluation attempt limit     | `180s`                  | The same, for each internal evaluation call.                                                                    |
| Preamble budget              | `30s`                   | The preamble or tool announcement is skipped if not written within this.                                        |
| Schedule poll interval       | `30s`                   | Every replica checks the shared job table this often; also the delay before retrying a failed dispatch.         |
| Schedule claim lease         | `120s`                  | A claimed-but-undispatched job from a crashed replica becomes claimable again after this.                       |
| Schedule retry backoff       | `60s` base, `3600s` cap | Between execution attempts of one tick when `max_attempts` > 1; doubles per attempt.                            |
| Schedule history retention   | `30` days               | Finished job rows older than this are pruned from the job table.                                                |
| Startup failure exit window  | `10s`                   | Boot errors exit the process non-zero within this window.                                                       |
| Attachment size              | `20 MB`                 | Largest PDF or Excel file the chat stores; Word and text files stop at `16 MB`, images at `8 MB`.               |
| Attachments per conversation | `10`                    | Further attaches answer `409`.                                                                                  |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.interactive.ai/agents/reference/limits-and-defaults.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
