DeepSeek-Reasonix/docs/AGENT_COMPOSITIONS.md

owner, backup, status, reviewed

owner	backup	status	reviewed
@SivanCola	@esengine	active	2026-10-18

Session Agent compositions

Studio's Agent presets page manages a persona together with tools, skills, MCP servers, extensions, hooks and custom commands. A composition is independent of the model, reasoning effort and the existing balanced/delivery role setting. It uses Reasonix's runtime; it does not load Harness's Cordis plugins.

Choosing and editing

Choose the mode at the left of the composer status row before the first prompt. One menu lists compositions with their sources and capabilities; Manage Agent presets… opens the management page below the choices. Once a prompt is accepted, the conversation keeps its binding.

The trigger shows only the mode name and arrow. Source and lock information stay in the menu and accessible label; run status and token counts sit at the right.

Queued work, pending questions and background jobs also prevent switching. The locked selector offers a new conversation with another composition. Clearing or rewinding an existing composition does not unlock it.

Two built-in cards sit above the separate custom-preset section:

Mode	Behavior
Standard (builtin:general)	Inherit current configuration for everyday code, file and research work. The stable ID preserves existing defaults.
Minimal (builtin:minimal)	A concise system persona, terminal (bash) and image reading (view_image), with native context compaction. Requires a vision-capable model.

Minimal loads no custom skills, commands, MCP, extensions, hooks or subagents. It retains the host controls needed to answer and ask questions. Its terminal can still modify files and access the network under existing permissions and sandbox rules; Minimal is not a read-only mode.

Missing image capability or disabled tools produce an explicit dependency error rather than another tool set.

Code review and Research are no longer built-in catalog entries. Their existing conversations retain the original binding. An old default pointing to a retired entry reports a diagnostic until an available default is explicitly chosen.

Copy a built-in to customize it. Each module group either inherits configuration when a conversation binds, or uses only the selected IDs. An empty explicit selection disables the group. The editor lists locally available modules; imports preview missing dependencies without installing or launching them.

Saving creates a definition revision. Existing conversations retain their resolved persona, parameters and resources. The page displays the definition revision beside the conversation's bound revision and reports stale-save conflicts while preserving the draft. Models remain independently selectable.

Files and retained resources

Item	Location
Personal definitions	<state>/agent-presets/definitions/<id>.json
Shared definitions	<workspace>/.reasonix/agent-presets/definitions/<id>.json
Definition revisions and explicit defaults	<state>/agent-presets/
Local authorization records and retained files	<state>/trusted/agent-presets/

<state> is Reasonix's resolved state root, including relocation. IDs start with builtin:, user: or project:. A project binding also records its workspace. Matching display names coexist; one scope never shadows another.

Project files cannot select a default: workspace defaults are the user's explicit choice, stored in personal state.

Definitions use schemaVersion: 1. Writes use atomic replacement and an expected revision.

Exported definitions contain references rather than credential values and never contain extension binaries. MCP supports args, url, env, headers, callTimeoutSeconds and startupTimeoutSeconds; extensions support args, env and timeoutMillis.

Parameter names are validated. Environment/header overrides require ${NAME} references. Presets cannot replace an installed extension's executable declaration.

Inherited choices resolve once at binding. Retained skill and hook files and extension code do not follow subsequent source edits.

Hooks retain referenced files and sibling bundles for common script formats. Bundles must fit the resource limit and cannot contain credential files or symbolic links.

Keep hook code in a dedicated directory; retain credentials through environment references. External interpreters and services keep their existing platform/authorization contracts.

Credential lookups remain with the existing credential/configuration owner. Sessions use separate MCP connections and process state, and extensions run from private copies. Existing trust, revocation, authorization and sandbox checks still apply.

A binding is local transcript metadata and never enters provider messages. Composition transcripts use native event-log schema 4; older readers refuse them instead of continuing with another tool set. Legacy transcripts keep their compatibility path and are not assigned today's default on restore.

Untrusted or unavailable bindings can be opened for history without launching modules; continuation is blocked. Deleting a definition does not remove its conversation's retained binding.

Native JSON exports use the reasonix-native-session version 2 envelope and include the authoritative event-log binding and retained resources. Import them under Settings → Storage. Import never creates local authorization records or starts programs.

Configuration backup version 3 also includes personal preset definitions and their default selection.

MCP tool contracts are pinned at binding. A changed tool catalog after refresh or reconnect blocks execution instead of silently replacing schemas. Package MCP processes and extension sidecars use private package copies; shutdown and failed assembly release their private directories.

The nonempty legacy user persona migrates once to a personal default preset. The original configuration remains. /persona reads and edits that personal default rather than maintaining a second mutable persona. Migration retries reuse an already written revision and preserve conflicting personal IDs.

Entry points

CLI: reasonix --agent-composition builtin:minimal, or reasonix run --agent-composition user:my-agent "Review this change". /agent lists compositions; /agent user:my-agent selects one in a blank interactive conversation. /preset retains its balanced/delivery meaning.

ACP exposes an independent agent_composition configuration option and narrows it to the current choice after the conversation starts. Remote sessions use the remote host's catalog, credentials and retained resources.

HTTP method and route	Request / result
GET /agent-presets	Catalog, effective default, module IDs and diagnostics
GET /agent-presets/{id}	Definition and revision
POST /agent-presets	{definition, expectedRevision} → saved version
DELETE /agent-presets/{id}?revision=...	Delete the matching declaration
POST /agent-presets/default	{id, workspace}
GET /agent-presets/{id}/export	Portable definition JSON
POST /agent-presets/import	{content} → {definition, diagnostics} preview
GET /agent-composition	Current binding summary, including lock/unavailability
POST /agent-composition	{id} → selected summary
POST /runtimes	Existing create fields plus optional agentComposition
POST /tree/sessions/export	{path} → {name, content}; native envelope for bound sessions
POST /tree/sessions/import-native	{workspace, content} → imported {path, agentComposition}

/status and runtime listings include agentComposition. Refusals use stable agent_composition.invalid, .not_found, .read_only, .conflict, .locked and .unavailable codes. The Studio catalogs translate these into Chinese and English.

Preset names, revisions and diagnostics do not enter the cached provider prefix. First use of a different composition can have a cold cache; editing a preset never rewrites a running conversation's prefix.