Codex and Claude agent learners

Use evolver.name: codex or claude when a learner should inspect trajectories, use tools, and edit an adapter directory over several actions. This is useful for skills, multiple files, and tool code that a single text rewrite does not capture well. On the single-file prompt-only template, the Codex learner is the prompt-only method.

Requirements and setup

Install and authenticate the selected learner CLI in the environment where training runs. Sandboxed program execution uses Linux and bubblewrap. The acting pipeline can use a different model or host.

evolver:
  name: codex
  resume: false
sandbox:
  enabled: true
  network: restricted

Complete the endpoint grants, environment, and task resources for your learner; the fragment alone is not a working model configuration. Use Installation and configuration boundaries.

Update contract

The learner edits the working adapter using the step’s learning material and EVOLVER.md. The Trainer owns acceptance and Git history. Files outside the learnable rules are rejected or repaired. For a performance gate, the method must explicitly evaluate and select candidates; file checks alone do not provide one.

Persistent learner state, host conversation resume, and Trainer crash recovery are separate mechanisms. Only enable evolver.resume for a backend that declares support; check reports unsupported requests.

Defaults

Codex:

description: A Codex agent improves the adapter from the step's learning material.
class: hermit.evolver.agent:AgentEvolver
needs: []
params:
  backend: codex
  prompt: START.md
  resume_prompt: RESUME.md
  args: []
  model: null                # the agent's model; null: its default
  price: null                # USD per million tokens {input, cached_input, output}
  home: [auth.json, .credentials.json]   # files of the agent's home copied into the run's
  tools: null                # the only Trainer tools the agent may use, e.g. [check_spec]; null: all
  hide: null                 # paths hidden from the agent besides examples/tests/docs/.git; null: nothing hidden

Claude:

description: A Claude Code agent improves the adapter from the step's learning material.
class: hermit.evolver.agent:AgentEvolver
needs: []
params:
  backend: claude
  prompt: START.md
  resume_prompt: RESUME.md
  args: []
  model: null                # the agent's model; null: its default
  price: null                # USD per million tokens {input, cached_input, output}
  home: [auth.json, .credentials.json]   # files of the agent's home copied into the run's
  tools: null                # the only Trainer tools the agent may use, e.g. [check_spec]; null: all
  hide: null                 # paths hidden from the agent besides examples/tests/docs/.git; null: nothing hidden

prompt and resume_prompt name learner instructions; args passes CLI arguments. Inspect the built-in definition before replacing prompts. For a custom learner harness, use AgentEvolver or CommandEvolver.

Report usage outside the framework’s metered tools so budget records remain meaningful. A learner’s direct external calls are not automatically accounted for merely because the Trainer launched it.

Learner tool access

Agent-backed learners can set evolver.params.tools to an allowlist such as [check_spec]; null exposes all Trainer endpoint tools. The gate refuses calls outside that list. Inspect the selected method’s defaults and hermit/evolver/gate.py. This controls the learner’s Trainer-tool endpoint, separately from the acting agent’s task/adapter tools. It does not make arbitrary shell commands safe or impose a mandatory check order.

For a complete task-specific Codex configuration, see examples/clbench_poker/prompt_only/run.yaml. Acting agents are configured under agent; evolver.name: codex selects the learner, not the acting host.