1
0
Fork 0
Code Issues Pull requests Projects Releases 2 Packages Wiki Activity Actions Pages

Close Milestone 2 with measured evidence

This commit is contained in:
Andraxion 2026-07-29 10:22:56 -04:00
parent fb0df5e4a1
commit 4c5773c865
10 changed files with 771 additions and 9 deletions

View file

@ -6,14 +6,14 @@ Goal: Let one project-bound server return compact, task-shaped, explainable cont
In scope: Capability modes; capability-aware bootstrap; versioned retrieval plans and context capsules; task-shaped context; generation diffs; evidence-gap diagnostics; generated client configuration; doctor checks.
Out of scope: Independent render-plan packages; adapter SDK expansion; self-hosting; storage replacement; embeddings; WorldForge or ScrapeStation changes; production MCP repointing; tags and releases.
Done when: Policy and capabilities are explicit; bootstrap recommends only available actions; task context is compact, deterministic, provenance-bearing, and bounded; generation and evidence gaps are explainable; generated configuration and doctor checks are safe and tested; the complete repository gate and Milestone 2 benchmark pass.
Status: Candidate frozen. Effective policy, versioned task retrieval, latest-generation diff
receipts, and logarithmic task-context page packing are committed and pushed on `dev`.
Deterministic client configuration and the read-only integration doctor now pass their bounded
publication, path-race, malformed-input, redaction, and no-hidden-work audits. The complete
repository gate passes with 205 tests and 120 subtests. A disposable 1,000-node audit sample passes
the maintained task-context, generation-diff, response-size, counter, and memory gates. Final
clean-revision benchmark evidence and documentation closeout remain before the milestone is marked
complete.
Status: Complete. Effective policy, versioned task retrieval, latest-generation diff receipts,
logarithmic bounded page packing, deterministic client configuration, and the read-only integration
doctor are implemented and contract-tested. The complete repository gate passes with 205 tests and
120 subtests. Three independent adversarial audits found no remaining implementation blocker. The
clean 1,000-node baseline is recorded against candidate commit
`fb0df5e4a1c591c2a84788fd4814d98550f11863`, including task/generation reconstruction,
response-size behavior, zero-hidden-work counters, and isolated memory. No tag or release was
created, no production integration was repointed, and self-hosting remains out of scope.
```
Milestones 35 remain directional context and are not active.