Autoresearch — Autonomous Goal-directed Iteration

Safety Invariants (all subcommands)

• Never push, publish, or deploy without explicit user approval.
• Bounded by default. Override with Iterations: unlimited.
• All results logged to autoresearch/{subcommand}-{YYMMDD}-{HHMM}/ directory.
• Chain handoff via handoff.json. Evals reads *-results.tsv.

Dispatch (bare /autoresearch)

Parse the invocation in this order:

Print a banner on every invocation: [autoresearch] mode: classic | orchestrator | wizard.

Subcommands

Universal Flags

Orchestrator

Activated when a plain-language goal is given without Metric:/Verify:. Classifies the goal into a Goal archetype — see references/orchestrator-routing.md for the archetype table and router decision table.

Two modes based on archetype:

• Orchestration loop — predicate-bearing archetypes (ship-ready, optimize-metric, fix-broken, harden, build-feature, explore). Goal has a mechanical Success predicate; the loop runs until that predicate is met.
• Single-pass dispatch — subjective/terminal archetypes (document, what-to-build, decide-design). Routes once to the fitting subcommand (learn / improve / reason), lets it self-terminate, then reports. No loop, no Plateau, no ship gate.

Orchestration Loop Steps

1. Classify — archetype label + mode.
2. Derive predicate — concrete Success predicate: exact shell command + expected output.
3. Confirm — archetype, mode, concrete predicate (command + expected output).
4. Round-0 dry-run — prove the predicate command runs and returns a value; safety-screen every derived command via screen-cmd.
5. Loop until predicate satisfied: a. Assess state via cheap signals (failing tests, error counts). b. Route to next subcommand. c. Run subcommand (inner loop). d. Keep changes that improve metric/reduce errors; rollback regressed changes.
6. Stop conditions: Predicate met (100% success), Plateau detected, Ceiling reached, or Blocked.