Token Saver 75+ with Model Routing

Core Principle

Request Classifier (silent, every message)

Model Routing Table

Routing via sessions_spawn

When to spawn (MANDATORY)

• Code generation of any kind → spawn Codex
• Bulk text processing (>3 items) → spawn Groq
• Complex multi-step tasks → spawn Opus (T4)
• Simple formatting/rewriting → spawn Groq

When NOT to spawn

• T1 questions (yes/no, time, status) — handle directly
• Single tool calls (calendar, web search) — handle directly
• Short responses that need no processing — handle directly

Spawn patterns

Groq (free bulk work):

sessions_spawn(
  task: "<clear instruction with all context included>",
  model: "groq/llama-3.1-8b-instant"
)

Codex (all code):

sessions_spawn(
  task: "Write <language> code that <detailed spec>. Include comments. Output the complete file.",
  model: "openai/gpt-5.3-codex"
)

Opus (T4 strategy):

sessions_spawn(
  task: "<full context + goal>. You have full tool access. Use sessions_spawn with Codex for code and Groq for bulk subtasks.",
  model: "anthropic/claude-opus-4-6"
)

Critical spawn rules

• Include ALL context in the task string — spawned agents have no conversation history
• Be specific — vague tasks waste tokens on clarification
• One task per spawn — don't bundle unrelated work
• For code: always use Codex — never write code yourself

Output Compression (applies to ALL tiers, ALL models)

Templates

• STATUS: OK/WARN/FAIL one-liner
• CHOICE: A vs B → Recommend: X (1 line why)
• CAUSE→FIX→VERIFY: 3 bullets max
• RESULT: data/output directly, no wrap-up

Rules

• No filler. No restating the question. Lead with the answer.
• Bullets/tables/code > prose.
• Do not narrate routine tool calls.
• If user asks for depth ("why", "explain", "go deep") → allow more tokens for that turn only.

Budget by tier

Tool Gating (before ANY tool call)

• Already known? → No tool.
• Batchable? → Parallelize.
• Can a spawned Groq handle it? → Spawn instead of doing it yourself.
• Cheapest path? → memory_search > partial read > full read > web.
• Needed? → Do not fetch "just in case."

Failure Protocol

• If Groq spawn fails → retry with GPT-5.2
• If Codex spawn fails → retry with GPT-5.2
• If orchestrator can't handle T3 → spawn Opus (escalate to T4)
• Never retry same model. Escalate.

Measurement (when asked or during testing)