mirror of
https://github.com/boshu2/agentops.git
synced 2026-09-14 15:08:13 +08:00
3213afcf1c
## Change Make native coding-agent execution the default AgentOps entry path with zero mandatory skills. Preserve full bundles and add repeatable `ao skills link --skill NAME` selection, validating the entire selection before writes. Align product, installation, architecture and generated command documentation. Extend the existing trial readout to separate endpoint test results, execution state and independently accepted work. Bind supplied judgments to exact content, acceptance and native evidence. Reject empty implementation subjects and require the caller's complete criterion ID set before reporting acceptance. Preserve genuine nonempty and deletion-only subjects, valid failures and missing-proof outcomes. ## Validation - Native onboarding from empty home/consumer directories produces no setup files; selective/full linking and failure boundaries are covered. - Actual RED/GREEN regressions cover empty subjects and the partial-criterion omission found by independent review. - Full Go build, vet and race/shuffle tests; affected Go lint; 88 Python readout/statistics tests passed. - All 73 gates, generated projections, strict documentation build and local aggregate passed (10 passed; one documented optional absence). - All nine PR checks succeeded at `7df0d42b12f35ffc22008cc10a40339afcfbb6a0`. - Fresh author-distinct review passed all six acceptance criteria over all 59 changed paths, with no findings or unchecked scope, after repairing the criterion-coverage finding. ## Evidence limits The real native coding repair demonstrates usability, not comparative skill uplift. The strict live-session machine replay remains NOT_PROVEN where execution/identity observations are unavailable; the source review PASS is retained separately. Existing cohort limits and the historical aggregate-enforcement gap remain unwaived. No new comparative cohort, scheduler, skill-corpus deletion, memory migration or global installation is included.
54 lines
2.4 KiB
Markdown
54 lines
2.4 KiB
Markdown
# Program
|
|
|
|
This repository defaults to native execution with optional skills (ADR-0017). PROGRAM is
|
|
repository execution guidance, not a product retry or delivery controller.
|
|
|
|
## Experiment unit
|
|
|
|
One invocation consumes and produces:
|
|
|
|
1. one resolved caller-owned intent, planning only when needed and a content
|
|
snapshot only when necessary;
|
|
2. bounded implementation and checks, with direct repair of known defects and
|
|
evidence-based approach revision within unchanged acceptance;
|
|
3. one runtime-derived subject manifest and factual check receipts with
|
|
complete or honestly incomplete changed-path proof;
|
|
4. fresh author-distinct native judgment over exact content, with fresh
|
|
re-validation after acceptance-relevant repairs;
|
|
5. a subject-led report, with a durable verdict only when requested or required
|
|
by a declared consumer.
|
|
|
|
Finish when acceptance is met and freshly validated. A true causal stall admits
|
|
at most one bounded fresh helper within the existing allowance; cancellation,
|
|
refusal and spent hard resources stop work. Do not renew an allowance through
|
|
replanning, compaction or delegation. Changed acceptance requires caller
|
|
authority. Repository Git and release procedures remain separate.
|
|
|
|
## Mutable scope
|
|
|
|
- product and doctrine: `README.md`, `PRODUCT.md`, `GOALS.md`, `PROGRAM.md`, `AGENTS.md`;
|
|
- implementation: `cli/**`, `skills/**`, `schemas/**`, `scripts/**`, `tests/**`;
|
|
- generated projections: `skills-codex/**`, registries, routers, maps, CLI docs;
|
|
- repository checks and docs: `.github/workflows/**`, `docs/**`, `evals/**`.
|
|
|
|
Secrets, credentials, user configuration outside the repository, production
|
|
data, release tags, package publication, and unrelated user edits remain outside
|
|
ordinary implementation authority.
|
|
|
|
## Evidence
|
|
|
|
Use the cheapest targeted checks during implementation. Before reporting the
|
|
complete change, run the ordinary deterministic suite appropriate to the final
|
|
surface and obtain one fresh independent judgment. Record exactly what was checked
|
|
and not checked.
|
|
|
|
The repository may then commit, push, merge, release, or roll back through its
|
|
normal Git/CI policy. Those transitions cannot upgrade or replace the semantic
|
|
verdict.
|
|
|
|
## Concurrency
|
|
|
|
One writer is the default. User-requested parallel work requires disjoint write
|
|
scopes and isolation. Factory adapters may dispatch explicit disjoint packets
|
|
once; they do not select work, retry, validate, integrate, or deliver.
|