the-teacher

the-teacher/active_harness

Instructions file

Instructions for the-teacher/active_harness, covering claude.md, what this is, commands, build gem artifact and bump patch version, sync, and release to rubygems.

the-teacher/active_harness

Agent

ActiveHarness divides errors into two categories: retryable and non-retryable. Retryable errors trigger automatic retries with exponential backoff, then move to the next fallback model. Non-retryable errors abort the entire chain immediately.

the-teacher/active_harness

Agent

All hooks are registered with on, before, after, or callback at the class or instance level.

the-teacher/active_harness

Agent

ActiveHarness agents can transcribe audio natively via OpenAI's or OpenRouter's speech-to-text endpoints. Enable it with transcribe true and use the same model/fallback DSL as any other agent.

the-teacher/active_harness

Agent

Every object that makes an LLM call exposes #executiontime (seconds, rounded to 3 decimal places).

the-teacher/active_harness

Agent

ActiveHarness agents can generate images natively — no customllmbackend/RubyLLM required. Enable it with image true and use the same model/fallback DSL as any other agent.

the-teacher/active_harness

Agent

Before every call, ActiveHarness automatically normalizes @input by stripping leading and trailing whitespace and collapsing internal whitespace sequences to a single space.

the-teacher/active_harness

Agent

ActiveHarness automatically calculates the monetary cost of every LLM call and attaches it to the Result object.

the-teacher/active_harness

Agent

When a model returns a transient error (TimeoutError, RateLimitError, ServerError, ProviderUnavailableError), ActiveHarness automatically retries the same model with exponential backoff before moving to the next fallback.

the-teacher/active_harness

Agent

When a provider returns token counts, they are available on the Result object under #usage. Not all providers return usage — the value is nil for streaming calls and some free-tier models.

the-teacher/active_harness

Agent

Right now, "is this agent going to work?" can only be answered by actually calling it. Validation is scattered and inconsistent.

the-teacher/active_harness

Agent

ActiveHarness could let agents accept images as input alongside a text prompt — "look at this and tell me X" — reusing the model chain, hooks, retry/fallback, and systemprompt machinery that already exists for text agents.