Profiles

Profiles define the agent's identity, tools, and behaviour for a specific domain.

Profile definition (`navi/profiles/base.py`)

Each profile is loaded from a directory under navi/profiles/<id>/:

config.json — all fields below
system_prompt.txt — domain-specific instructions
subagent_system_prompt.txt — injected into subagents spawned from this profile (optional)

All `config.json` fields

Identity

Key	Type	Default	Description
`id`	str	required	Unique profile identifier (matches directory name)
`name`	str	required	Human-readable name shown in UI
`description`	str	required	Longer description shown in profile picker
`short_description`	str	`""`	One-line summary injected into every profile's system prompt (cross-profile awareness)
`full_description`	dict	`{}`	Structured dict: `specialization`, `when_to_use`, `key_tools` keys

LLM

Key	Type	Default	Description
`llm_backend`	str	`"ollama"`	Backend key: `"ollama"`, `"openai"`
`model`	str or list[str]	`["gemma4:31b-cloud"]`	Model priority list — first available wins. String is accepted and auto-wrapped.
`temperature`	float	`0.7`	Sampling temperature for main loop calls
`max_iterations`	int	`10`	Hard cap on tool-calling iterations per turn
`top_k`	int \	None	`None`	Ollama sampling top_k
`top_p`	float \	None	`None`	Ollama sampling top_p
`num_thread`	int \	None	`None`	CPU threads for local inference. `None` = Ollama default

Tools

Key	Type	Default	Description
`enabled_tools`	list[str]	required	Tool names available in the main loop
`subagent_tools`	list[str]	`[]`	Tools available to sub-agents spawned from this profile. Falls back to `enabled_tools` (full list) if empty.

spawn_agent may receive an optional profile_id. If omitted, the subagent uses the parent session's current profile. If provided, the subagent uses the selected profile's model, prompt, planning flags, and subagent_tools/enabled_tools fallback.

Thinking mechanics

Key	Type	Default	Description
`think_enabled`	bool	`true`	Pass `think=True` to LLM on every call (extended reasoning). Disable for latency-sensitive profiles.
`iteration_budget_enabled`	bool	`true`	Inject remaining iteration count into context so the model knows when to wrap up.
`goal_anchoring_enabled`	bool	`true`	Inject a goal-reminder system message every N iterations to prevent drift.
`goal_anchoring_interval`	int	`5`	N for goal anchoring.
`anti_stall_enabled`	bool	`true`	Detect looping without todo progress and inject a hard warning.
`anti_stall_threshold`	int	`8`	Consecutive iterations without progress before stall warning fires.
`step_validation_enabled`	bool	`false`	Reserved flag — todo validation is unconditional in the current implementation.
`adaptive_replan_enabled`	bool	`false`	When a todo step is marked failed, trigger a re-planning pass. Depends on `step_validation_enabled`.

Planning

The planning pipeline runs before the main tool-calling loop and produces a structured execution plan. It has three phases:

Phase 1 — Analysis: reformulates the task, identifies subtasks and unknowns. Can output DIRECT to skip to execution immediately.
Phase 2 — Structured review: one LLM call critiques the Phase 1 analysis through Critic / Pragmatist / Detailer sections and emits Plan Adjustments. Runs only when Phase 1 signals REFLECT: yes.
Phase 3 — Execution plan: assigns each subtask to TOOL / AGENT / SELF and uses adaptive plan depth.

Key	Type	Default	Description
`planning_enabled`	bool	`false`	Run the planning pipeline on every user message (not just the first). First-message planning always runs regardless of this flag.
`planning_mandatory`	bool	`false`	`true` — the `DIRECT` shortcut is never offered to the model; all three phases always run. `false` — the model can output `DIRECT` in Phase 1 to skip straight to execution. First-message planning is always forced regardless of this flag.
`planning_phase1_enabled`	bool	`true`	Enable Phase 1 (task analysis). When disabled, Phase 3 runs without analysis context.
`planning_phase2_enabled`	bool	`false`	Enable Phase 2 structured review. Adds one LLM call only when Phase 1 signals `REFLECT: yes`.
`planning_phase3_enabled`	bool	`true`	Enable Phase 3 (structured execution plan). When disabled, only Phase 1 (analysis) runs.

Sub-agent planning

Key	Type	Default	Description
`subagent_think_enabled`	bool \	None	`None`	Extended reasoning for sub-agents. `None` = inherit `think_enabled` from parent profile.
`subagent_planning_enabled`	bool	`false`	Sub-agents spawned from this profile also run the planning pipeline before their tool loop.
`context_providers`	list[str]	`[]`	Extra context providers to inject for this profile (by name). Global providers are always injected.
`mcp_servers`	dict	`{}`	MCP servers referenced by this profile. Format: `{"server_name": ["group1", "group2"]}` or `{"server_name": ["*"]}` for all tools.
`is_admin_only`	bool	`false`	If `true`, profile is hidden from non-admin users in the profile list.

Active profiles

ID	Name	Models (priority order)	Temp	Planning
`secretary`	Personal Secretary	gemma4:31b-cloud → gemma4:26b-a4b-it-q4_K_M	0.65	Yes
`server_admin`	Server Administrator	gemma4:31b-cloud → gemma4:26b-a4b-it-q4_K_M	0.3	Yes
`developer`	Developer	gemma4:31b-cloud → gemma4:26b-a4b-it-q4_K_M	0.45	Yes
`tool_developer`	Tool Developer	gemma4:31b-cloud → gemma4:26b-a4b-it-q4_K_M	0.35	Yes
`discuss`	Discussion	gemma4:31b-cloud → gemma4:26b-a4b-it-q4_K_M	0.85	No
`modeler_3d`	3D Modeler	gemma4:26b-a4b-it-q4_K_M → gemma4:31b-cloud	0.35	Yes

All profiles share a base tool set. User tools from tools/enabled.json are merged in at runtime.

System prompt construction

The LLM sees (injected fresh on every call, never stored in session):

{persona.txt content}

---

{profile system_prompt.txt content}

persona.txt — global layer: personality, CONTEXT FIRST principle, self-extension rules, scratchpad/todo/memory instructions, delegation rules.

system_prompt.txt — domain layer: tool priorities, workflow, safety rules for this profile.

Adding a profile

Create directory navi/profiles/my_profile/

Add config.json (minimal example):

{
"id": "my_profile",
"name": "My Profile",
"description": "...",
"short_description": "...",
"model": ["gemma4:31b-cloud", "gemma4:26b-a4b-it-q4_K_M"],
"temperature": 0.5,
"max_iterations": 20,
"enabled_tools": ["todo", "scratchpad", "mcp:navi-web:web_search", "filesystem"],
"subagent_tools": ["todo", "filesystem", "terminal"],
"planning_enabled": true,
"planning_mandatory": false,
"planning_phase1_enabled": true,
"planning_phase2_enabled": false,
"planning_phase3_enabled": true,
"think_enabled": true,
"iteration_budget_enabled": true,
"goal_anchoring_enabled": true,
"goal_anchoring_interval": 5,
"anti_stall_enabled": true,
"anti_stall_threshold": 8,
"step_validation_enabled": false,
"adaptive_replan_enabled": false,
"subagent_planning_enabled": false
}

Add system_prompt.txt with domain-specific instructions.
Optionally add subagent_system_prompt.txt.
The profile is auto-discovered at startup — no registration needed.

Profile switching

switch_profile tool updates session.profile_id in the DB. After each tool execution batch, run_stream() checks for a profile change and reloads profile + tools. Takes effect on the next LLM call.

Rules (in persona): don't switch for a single off-topic question; switch when the domain clearly changes; never switch back and forth repeatedly.