Skip to content

Docs Map

This page explains what each document is for so readers do not have to guess which page contains narrative guidance versus generated reference.

Start here

Doc Purpose
index.md Landing page and reading order.
getting-started/use-cases.md Practical end-to-end examples for common batchor workflows.
getting-started/python-api.md End-to-end Python usage patterns.
getting-started/cli.md Operator CLI behavior and examples.
reference/api.md Public symbols and generated API reference.

Design docs

Doc Purpose
design_docs/BOUNDARY_AND_PHILOSOPHY.md Ownership boundary between batchor, storage/artifacts, and user pipelines.
design_docs/ARCHITECTURE.md Canonical runtime diagrams, package structure, main flows, and extension seams.
design_docs/OPENAI_BATCHING.md OpenAI request construction, token budgeting, splitting, and batch polling behavior.
design_docs/ANTHROPIC_BATCHING.md Anthropic Message Batches request construction, polling, result parsing, limits, and retention.
design_docs/GEMINI_BATCHING.md Gemini text-only request construction, batch polling, response parsing, and current limits.
design_docs/STORAGE_AND_RUNS.md Durable Run lifecycle, rehydration, checkpoints, control state, artifact retention, and operator semantics.
design_docs/STORAGE_MIGRATIONS.md SQLite schema-versioning and migration guidance.
design_docs/RUNTIME_DURABILITY_0_0_7.md Release design, boundaries, and verification contract for the 0.0.7 runtime-durability changes.
design_docs/ROADMAP.md Intentionally unimplemented areas and planned work.

Validation and project policy

Doc Purpose
smoke-test.md Minimum validation bar for local work and CI.
policies/support.md Published support policy for the latest released 0.x minor.
policies/versioning.md Versioning expectations for the Python API and CLI.
policies/contributing.md Contribution guidance.

Recent implementation areas

  • Deterministic built-in source checkpoints now cover CSV, JSONL, and Parquet.
  • Library-first run control now includes pause, resume, and drain-style cancel.
  • Incremental terminal-result reads/exports are documented in the Python API and storage docs.
  • Raw output/error artifact retention is now configurable per run through ArtifactPolicy.
  • Gemini text-only Batch support is available through the Python API and default provider registry.
  • Anthropic Message Batches support is available through the Python API, CLI, and default provider registry.