Bo
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.
2.7 KiB
Architecture
AgentOps defaults to native execution with zero mandatory skills. Its small semantic core binds acceptance to exact content and fresh independent judgment; optional skills and adapters package guidance around that boundary.
existing bead or caller intent
-> on-demand planning and bounded implementation
-> runtime-derived subject-manifest.v1 + check receipts
-> fresh independent judgment
-> PASS | FAIL | NOT_PROVEN
-> direct repair and fresh revalidation within real bounds when needed
-> completed acceptance or truthful unfinished result
Optional workflow guidance
- Plan shapes missing intent and revises disproved approaches under unchanged acceptance and scope; clear work need not invoke it.
- Implement performs bounded implementation and direct known-defect repair and returns runtime-derived subject identity, actual changed paths, and factual check receipts.
- Validate identifies the exact subject without Git, checks scope and acceptance, and obtains one judgment from a distinct declared context. It stores a content-addressed verdict atomically only when requested by the caller or a declared downstream consumer.
- RPI owns the authorized outcome through checks, direct repair and fresh final judgment; specialists and planning are on demand (ADR-0017).
- Memory optionally recalls reviewed topic pages or separately mines and curates supported claims. It cannot change completed product verdicts.
Known findings are repaired within authority and real remaining bounds. A genuine causal stall admits at most one bounded fresh helper; an unhelpful answer, cancellation, refusal or a spent real bound ends the attempt. Explicit repair-round bounds still apply, and no invocation renews an allowance. The fixed-dispatch adapter keeps its narrower optional contract; it does not govern direct native execution.
Hexagonal boundary
The core depends on contracts, not substrates. NTM, Agent Mail, Codex Exec, managed agents, Git metadata, trackers, provenance, and councils are optional adapters or strategies. Missing or corrupt adapters cannot change a core outcome.
Generic provenance may record a verdict after one is persisted. Provenance and artifact storage are never required for a fresh validation result to be valid.
Repository boundary
ao gate check runs ordinary deterministic repository checks. A successful
check says only that those checks passed. Repository policy owns commits,
pushes, pull requests, CI, releases, rollback, and deployment.
See the component map, ports and adapters, and public contracts.