Skip to main content

​
Goal Management

Goals transform Myrm from a chat assistant into an autonomous worker. Define an objective, set constraints, and let the agent work independently across multiple turns.

​
Creating a Goal

​
From the GUI

  1. Navigate to the Goal panel in the sidebar
  2. Click New Goal
  3. Describe the objective (e.g., “Refactor the authentication module to use JWT tokens”)
  4. Optionally set acceptance criteria, constraints, and budget limits
  5. Submit — the agent begins planning and executing

​
From Chat

Simply describe a complex task in natural language. The agent will detect it requires sustained effort and offer to create a goal.

​
Goal Lifecycle

PENDING_APPROVAL → ACTIVE → PAUSED → COMPLETED / FAILED / CANCELLED
                              ↕
                           QUEUED
StateDescription
PENDING_APPROVALWaiting for user to approve the execution plan
ACTIVEAgent is actively working toward the objective
PAUSEDTemporarily halted (budget limit or user pause)
QUEUEDWaiting for the current active goal to finish
COMPLETEDObjective met and verified
FAILEDUnable to complete within budget
CANCELLEDExplicitly cancelled by user

​
Budget Control

Every goal has 4 budget dimensions:
DimensionDescriptionExample
max_tokensMaximum total tokens consumed500,000
max_usdMaximum dollar spend$5.00
max_time_secondsMaximum wall-clock time3600 (1 hour)
max_turnsMaximum agent turns30
Budget exhaustion pauses the goal with a structured summary of progress. You can resume the goal with additional budget at any time.

​
Acceptance Criteria

Define what “done” looks like: 
All tests pass, code coverage > 80%, no new linting errors
The agent uses dual-engine verification:
  1. Shell verification — Runs test commands (e.g., pytest, npm test) and checks results
  2. Semantic verification — LLM-based assessment against your acceptance criteria
Both engines must agree for the goal to be marked complete.

​
Constraints

Hard rules the agent must follow: 
Do not modify the database schema
Do not introduce new dependencies
Keep all changes backward compatible
Constraints are injected into the agent’s prompt every turn as a “CONSTRAINTS (MUST NOT VIOLATE)” block, and the semantic judge evaluates compliance during completion verification.

​
7-Step Continuation Guard

At the end of every turn, the continuation guard chain determines whether the agent should continue:
  1. Check if the user cancelled
  2. Check budget limits (all 4 dimensions)
  3. Check if tools reported completion
  4. Check semantic completion (LLM judge)
  5. Check constraint compliance
  6. Check for stalled progress
  7. Check if dynamic subgoals are satisfied
This prevents both premature termination and runaway execution.

​
Priority Queue

When you create multiple goals, they’re automatically queued:
  • The first goal runs immediately
  • Subsequent goals enter QUEUED state
  • When the active goal finishes, the next queued goal auto-starts
  • Drag-and-drop reordering in the GUI
Set auto_approve: true to skip the approval step for queued goals, enabling fully unattended execution of goal chains.

​
Dynamic Subgoals

During execution, you can add new objectives without interrupting the agent:
  1. Open the active goal’s detail panel
  2. Add a subgoal (e.g., “Also add unit tests for the new module”)
  3. The subgoal is injected into the agent’s context with highest priority
Subgoals are included in the semantic judge’s completion criteria.

​
Objective Hot-Edit

Change the goal’s direction mid-execution:
  1. Open the active goal’s detail panel
  2. Edit the objective text
  3. The change is injected as a steering message — the agent adjusts course without losing progress

​
Execution Summary

After completion, every goal produces a GoalExecutionSummary with:
  • Files modified (with diff links)
  • Token usage breakdown
  • Cost breakdown by model
  • Time elapsed
  • Turn count
  • Completion reason
This summary is available in the GUI and via API.

​
Example Workflow

User: "Migrate the API from Express to Fastify"

Goal created:
  Objective: Migrate Express → Fastify
  Criteria: All existing tests pass, no API contract changes
  Constraints: Don't modify the database layer
  Budget: max_turns=50, max_usd=$10

Agent:
  Turn 1-3: Plans migration, identifies 12 affected files
  Turn 4-15: Rewrites route handlers
  Turn 16-20: Updates middleware
  Turn 21-25: Fixes failing tests
  Turn 26: All tests pass, semantic judge confirms completion
  
Goal COMPLETED — 26 turns, $3.47 spent