# Milestone 2 closeout

## Outcome

Milestone 2 is complete. One project-bound server can expose an explicit effective policy and
return compact, task-shaped, explainable context. Users can generate deterministic client
fragments and inspect their bindings without hidden runtime work.

Implemented contracts:

- Version-1 effective policy and capability-aware bootstrap.
- Version-1 retrieval plans and context capsules.
- Bounded task-context pagination with evidence gaps and explicit omissions.
- One disposable latest-generation transition receipt and paged read surface.
- Deterministic Codex, Claude, and OpenClaw standalone configuration fragments.
- Fixed-inventory read-only doctor results.
- Dedicated configuration and doctor JSON schemas.
- Repository-native Milestone 2 contract, smoke, scale, response-size, counter, and memory gates.

## Candidate evidence

The frozen implementation candidate is
`fb0df5e4a1c591c2a84788fd4814d98550f11863`.

The complete repository gate passed:

- Ruff formatting and lint.
- HTML, rendered-manual HTML, CSS, and JavaScript checks.
- Pyright with zero diagnostics.
- Warning-strict compilation and tests.
- 205 tests and 120 subtests.
- Lock and npm dependency-tree checks.
- Wheel and source-distribution builds.
- Milestone 0, 1, and 2 smoke benchmarks.

Three independent read-only adversarial audits covered client publication and policy binding,
doctor race and malformed-input behavior, and benchmark/contract evidence. Reproduced descriptor,
parent, target, filesystem, policy, secret-redaction, ambiguity, parser, response-size, and hidden
work defects were fixed and regression-tested before the candidate was frozen.

The clean ten-sample 1,000-node benchmark passed every threshold. Exact measurements and counter
ranges are recorded in
[`MILESTONE_2_BASELINE.md`](MILESTONE_2_BASELINE.md) and
[`benchmarks/milestone2-2026-07-29.json`](../benchmarks/milestone2-2026-07-29.json).

## Preserved boundaries

- The `docforge` package, imports, CLI executable, MCP executable, and existing tool names remain.
- Legacy one-method `load_projection()` adapters remain supported.
- The no-AST shorthand and legacy adapter-policy payload remain compatible.
- Project descriptor schema version 1 remains unchanged.
- No storage replacement was introduced.
- No legacy DocForge MCP or DocForge2 self-hosting was used.
- WorldForge and ScrapeStation were not touched.
- No production MCP integration was repointed.
- The legacy Forgejo repository and `legacy` remote were not changed.
- No tag, release, release announcement, or visibility change was created.

## Known follow-up work

The next active milestone may improve projection independence. It must not silently absorb these
separate future ideas:

- Avoid recomputing a complete task capsule for every continuation page.
- Add authenticated cursors only if a stronger threat model requires them.
- Verify Claude's native timeout representation.
- Add versioned adapter-owned launcher metadata before generating custom-adapter configurations.
- Keep doctor read-only; a live connection test must be an explicit separate operation.