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

# Configuration reference

A one-page index of every setting that changes what the model reads on a turn -- where it's set, what it defaults to, and what it changes. Use this page to find the right lever quickly, then follow the link to the full reference for the syntax and examples.

ABL settings take effect in new conversations once saved, or once published and deployed for production channels. Project settings take effect on the next turn unless noted otherwise.

> [!NOTE]
>
> Knowledge-base and voice levers are covered in full on [Knowledge bases and knowledge tools](/agent-platform/knowledge) and [Voice agents](/agent-platform/channels/voice) -- this table includes only their headline entries.

| Setting | Where | Default | Changes |
| - | - | - | - |
| [`BEHAVIOR: role:`](/agent-platform/abl-reference/multi-agent-and-supervisor#behavior-settings) | Agent ABL | Not set (allow-list mode) | Which values reach `## Current Context`, and which prompt template is used -- see [How a turn is built](/agent-platform/context-and-prompts#what-the-model-sees-each-turn) |
| `GOAL`, `PERSONA`, `LIMITATIONS`, `{{refs}}` | Agent ABL | -- | The identity section; references also make values visible in `## Current Context` |
| `SYSTEM_PROMPT:` | Agent ABL | Catalog template | Replaces the template; runtime sections are still appended |
| [`MEMORY: SESSION:`](/agent-platform/memory-and-state#session-memory) | Agent ABL | -- | `## Session Memory` content, and what the model may write |
| [`MEMORY: persistent:`, `remember:`, `recall:`](/agent-platform/memory-and-state#persistent-memory) | Agent ABL | -- | Values loaded into the session; `recall: INSTRUCTION` lines in the prompt |
| [`HANDOFF … CONTEXT:`](/agent-platform/abl-reference/multi-agent-and-supervisor#handoff-context) (`pass`, `summary`, `history`, `memory_grants`) | Agent ABL | `history: full` | The receiving agent's history, context, and granted memory |
| [`DELEGATE … INPUT` / `PURPOSE`](/agent-platform/abl-reference/multi-agent-and-supervisor#delegate) | Agent ABL | -- | The only context a delegate gets |
| `CONVERSATION:` | Agent ABL | -- | `## Conversation Behavior` lines; listening and barge-in behavior on voice |
| [`EXECUTION.inline_gather`](/agent-platform/abl-reference/agent-declaration#configuration-properties) | Agent ABL | `false` (on in the voice profile) | `## Information Collection` instead of the `GATHER` list |
| [`EXECUTION.compaction.*`](/agent-platform/context-compaction#size-limits-and-compaction) | Agent ABL | See [Context size, compaction, and budgets](/agent-platform/context-compaction) | Tool results, earlier turns, and `## Current Context` budgets |
| `EXECUTION.models.summarization` | Agent ABL | Project tier | The model used for tool-result summaries |
| `EXECUTION.voice.instructions` | Agent ABL | -- | `## Voice Delivery Instructions` and voice formatting rules |
| `EXECUTION.guardrail_builtins` | Agent ABL | `false` | Whether a guardrail check can read `content`, `session_state`, and `tool_results` |
| [Tool `MODEL_CONTEXT`](/agent-platform/abl-reference/tools#model_context-on-a-tool-result) (`FIELDS` / `TEMPLATE`) | Tool ABL | -- | What the model sees of a tool result, now and later |
| [Response `MODEL_CONTEXT`](/agent-platform/abl-reference/flow#model_context-on-a-response) | Hook `RESPOND`, `COMPLETE`, `FLOW` step | -- | What the history records for a rich response |
| [Tool `compaction:`](/agent-platform/abl-reference/tools#result-compaction) (`essential_fields`, `summary_timeout_ms`, `max_search_tokens`) | Tool ABL | -- | Per-tool compaction, and the knowledge-base token budget |
| [Tool `store_result`](/agent-platform/abl-reference/tools#store-result) | Tool ABL | `true`; `false` once the tool has `on_result: SET` | Whether `last_<tool>_result` is kept |
| Tool param `default_source`, `visibility_model`, `visibility_trace` | Tool ABL | Visible | Hides a runtime-supplied value from the model and from traces |
| [KB `search_instructions`, `kb_name`, `description`](/agent-platform/knowledge#tool-level-search-settings) | Tool ABL / KB settings | -- | How and when the model searches |
| [Index Top K, similarity threshold, keyword weight](/agent-platform/knowledge#additional-settings) | Studio KB index settings | 10, 0.2, 0.5 | How many chunks come back |
| Citations | Studio KB citation settings | On by default, per index | Citation instructions added to the prompt |
| [`GUARDRAILS:`](/agent-platform/abl-reference/guardrails) | Agent ABL | -- | Per-agent checks -- see [Guardrail checkpoints](/agent-platform/safety-and-guardrails#guardrail-checkpoints) |
| Guardrail policies, providers, fail mode | Studio Govern → Guardrails | Fail open | Project and tenant checks; `## Current Policy` |
| [Project compaction](/agent-platform/context-compaction#where-to-set-compaction-policies) | Project runtime config (API or import) | Platform defaults | Project-wide budgets; resolved once per conversation |
| [Voice latency profile and overrides](/agent-platform/administration/general-settings#voice-low-latency-profile) | Studio Settings → Runtime Config | Auto-seeded for voice | Tighter budgets, fast model tier, reasoning off, inline gather on |
| Filler | Project runtime config | Profile defaults | Voice filler behavior and the status-update instruction |
| [PII redaction](/agent-platform/administration/general-settings#pii-redaction) (`pii_redaction`) | Project runtime config | On | Tokens in place of personal data in the prompt and in traces. Built-in detectors start off on new projects. |
| [Multi-intent](/agent-platform/administration/general-settings#multi-intent-recognition) | Project runtime config | -- | Multi-request routing and task sections |
| [Cross-channel recall](/agent-platform/administration/agent-behavior-settings#omnichannel) | Project omnichannel settings | Per project | `## Previous Conversations (Other Channels)`: up to 30 messages of 500 characters each |

> [!NOTE]
>
> Fixed by the platform, not configurable: the order of prompt sections, the Customer Output Contract, the tool-history marker and its 6-round window, the realtime voice handoff history-replay limits, and the absolute limits on `## Current Context` (40,000 characters per value, 100,000 for the whole block).

***

**Related articles:**

* [How a turn is built](/agent-platform/context-and-prompts) -- what each of these settings ultimately controls.
* [Context size, compaction, and budgets](/agent-platform/context-compaction) -- the compaction defaults in full.
* [Agent declaration](/agent-platform/abl-reference/agent-declaration) -- `GOAL`/`PERSONA`/`SYSTEM_PROMPT` and the `EXECUTION:` block.
* [Multi-agent and supervisor](/agent-platform/abl-reference/multi-agent-and-supervisor) -- `HANDOFF`, `DELEGATE`, and `ESCALATE`.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.