skills/boshu2__agentops
1
0
Fork 0
mirror of https://github.com/boshu2/agentops.git synced 2026-09-14 15:08:13 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
ao-pre-reduction@5b334a13f
boshu2__agentops/mkdocs.yml
T
Bo efc2609682 docs(architecture): formalize the L0-L4 autonomy ladder (ag-wrom #autonomy-ladder) (#787) 
## What

Closes the partial in Google-SRE convergence **point #8** (`ag-wrom`):
AgentOps already ran work at several autonomy levels (human-in-loop
in-session → substrate dispatch → bounded `autodev`) but the progression
was *implicit* — nothing named the rungs, stated what each may mutate,
or defined the evidence that earns a promotion. Implicit autonomy is how
a probabilistic agent quietly acquires more authority than its track
record justifies.

Adds `docs/architecture/autonomy-ladder.md`:

- **The invariant every rung obeys** — non-deterministic reasoning core
wrapped by a deterministic enforcement boundary (CI gates +
ports-and-adapters + ratchet) the agent can't bypass. The ladder moves
the *leash*, never relaxes the *boundary*. L4 code passes the same CI as
L0 code.
- **L0–L4 rungs** mapped to AgentOps' real dispatch vocabulary, with
human posture / acts-before-review / may-merge per rung.
- **Promotion gates** — per-lane, revocable, gated on
statistically-significant success vs Golden data at the
Bronze/Silver/Gold tier.
- **Demotion** — auto-downgrade on risk (the L3→L2 analog of Google's
de-escalation) + the unconditional Red Button.
- **Hard ceilings** — no rung confers authority over
external/secrets/schema/deletion/strategic-fork/merge-beyond-contract;
those stay draft-and-queue at every level.
- Honest divergence stated: AgentOps autonomy is **build-time** (code +
`.agents/` corpus), not run-time production ops — which is why L4 is
delegated to a substrate, not shipped (ADR-0009).

Wires it into the architecture index card grid + `mkdocs.yml` nav, and
flips convergence point #8 from ⚠️ partial to ✅ encoded (tally 9/1/1).

## Evidence
Closes-scenario: ag-wrom#autonomy-ladder
Bounded-context: BC1-Corpus
Evidence: markdownlint-cli2 PASS on all 3 changed docs; all cross-links
verified to resolve (operating-loop, canonical-loop-model,
fungibility-charter, google-sre, ADR-0009 in-docs relative; CLAUDE.md +
skills/autodev as GitHub URLs per repo convention for out-of-docs
targets); new page registered in mkdocs nav for `mkdocs build --strict`.
2026-06-06 12:18:20 +00:00

277 lines
9.4 KiB
YAML
Raw Permalink Blame History

site_name: AgentOps
site_description: Context compiler for coding agents. Assembles, validates, and delivers the right context so every session starts loaded, not cold.
site_url: https://boshu2.github.io/agentops/
site_author: AgentOps
repo_name: boshu2/agentops
repo_url: https://github.com/boshu2/agentops
edit_uri: edit/main/docs/
docs_dir: docs
site_dir: _site
# Operationalized methodology corpora are repo artifacts (kernel + operator library
# + validators + a fair-use quote bank), not website content — kept tracked in the
# repo but excluded from the published site (avoids re-hosting source material and
# keeps internal scaffolding out of nav/search).
exclude_docs: |
convergence/operationalized/
# Keep building even when the knowledge graph links outside docs/ (e.g., ../skills/).
# Strict link checking runs as a separate CI job via tests/docs/validate-links.sh + lychee.
strict: false
theme:
name: material
language: en
favicon: assets/favicon.svg
logo: assets/logo.svg
custom_dir: docs/overrides
palette:
# Dark mode default (slate) — toggle flips to light.
- media: "(prefers-color-scheme)"
scheme: slate
primary: custom
accent: custom
toggle:
icon: material/brightness-auto
name: Switch to light mode
- media: "(prefers-color-scheme: light)"
scheme: default
primary: custom
accent: custom
toggle:
icon: material/brightness-7
name: Switch to dark mode
- media: "(prefers-color-scheme: dark)"
scheme: slate
primary: custom
accent: custom
toggle:
icon: material/brightness-4
name: Switch to system preference
font:
text: Inter
code: Space Mono
icon:
repo: fontawesome/brands/github
edit: material/pencil
view: material/eye
features:
- navigation.tabs
- navigation.tabs.sticky
- navigation.sections
- navigation.expand
- navigation.indexes
- navigation.top
- navigation.footer
- navigation.instant
- navigation.instant.prefetch
- navigation.tracking
- search.suggest
- search.highlight
- search.share
- content.code.copy
- content.code.annotate
- content.action.edit
- content.action.view
- content.tabs.link
- content.tooltips
- toc.follow
extra:
generator: false
social:
- icon: fontawesome/brands/github
link: https://github.com/boshu2/agentops
name: AgentOps on GitHub
extra_css:
- assets/stylesheets/extra.css
markdown_extensions:
- abbr
- admonition
- attr_list
- def_list
- footnotes
- md_in_html
- tables
- toc:
permalink: true
permalink_title: Anchor link
- pymdownx.arithmatex:
generic: true
- pymdownx.betterem
- pymdownx.caret
- pymdownx.details
- pymdownx.emoji:
emoji_index: !!python/name:material.extensions.emoji.twemoji
emoji_generator: !!python/name:material.extensions.emoji.to_svg
- pymdownx.highlight:
use_pygments: true
linenums: false
anchor_linenums: false
pygments_lang_class: true
guess_lang: false
auto_title: true
- pymdownx.inlinehilite
- pymdownx.keys
- pymdownx.mark
- pymdownx.smartsymbols
- pymdownx.snippets:
check_paths: true
base_path:
- docs
- .
- pymdownx.superfences:
custom_fences:
- name: mermaid
class: mermaid
format: !!python/name:pymdownx.superfences.fence_code_format
- pymdownx.tabbed:
alternate_style: true
- pymdownx.tasklist:
custom_checkbox: true
- pymdownx.tilde
plugins:
- search:
separator: '[\s\-,:!=\[\]()"/]+|(?!\b)(?=[A-Z][a-z])|\.(?!\d)|&[lg]t;'
- gen-files:
scripts:
- docs/_hooks/gen_skill_pages.py
- docs/_hooks/gen_cli_reference.py
- section-index
- include-markdown
- git-revision-date-localized:
enable_creation_date: false
fallback_to_build_date: true
strict: false
type: date
nav:
- Home: index.md
- Getting Started:
- getting-started/index.md
- "AgentOps 3.0 (North Star)": 3.0.md
- Roadmap: ROADMAP.md
- Newcomer Guide: newcomer-guide.md
- Create Your First Skill: create-your-first-skill.md
- Behavioral Discipline: behavioral-discipline.md
- FAQ: FAQ.md
- Contributing: CONTRIBUTING.md
- Security: SECURITY.md
- Changelog: CHANGELOG.md
- Upgrading: UPGRADING.md
- Migrating to 3.0: MIGRATION-3.0.md
- Daemon Migration: daemon-migration.md
- Skills:
- skills/index.md
- Skills Reference: SKILLS.md
- Decision Tree: skills-decision-tree.md
- Skill API: SKILL-API.md
- Skill Router: SKILL-ROUTER.md
- Catalog: skills/catalog.md
- CLI:
- cli/index.md
- Command Reference: cli/commands.md
- CLI ↔ Skills Map: cli-skills-map.md
- Architecture:
- architecture/index.md
- How It Works: how-it-works.md
- Architecture Overview: ARCHITECTURE.md
- Software Factory: software-factory.md
- Intent-to-Loop Hexagon: architecture/intent-to-loop-hexagon.md
- Fungibility Charter: architecture/fungibility-charter.md
- Autonomy Ladder: architecture/autonomy-ladder.md
- Behavior-Shaping Environment: architecture/behavior-shaping-environment.md
- Codex Hookless Lifecycle: architecture/codex-hookless-lifecycle.md
- Primitive Chains: architecture/primitive-chains.md
- PDC Framework: architecture/pdc-framework.md
- FAAFO Alignment: architecture/faafo-alignment.md
- Failure Patterns: architecture/failure-patterns.md
- AO Command Customization: architecture/ao-command-customization-matrix.md
- Workflows:
- workflows/README.md
- Complete Cycle: workflows/complete-cycle.md
- Session Lifecycle: workflows/session-lifecycle.md
- Quick Fix: workflows/quick-fix.md
- Debug Cycle: workflows/debug-cycle.md
- Knowledge Synthesis: workflows/knowledge-synthesis.md
- Assumption Validation: workflows/assumption-validation.md
- Post-Work Retro: workflows/post-work-retro.md
- Multi-Domain: workflows/multi-domain.md
- Continuous Improvement: workflows/continuous-improvement.md
- Infrastructure Deployment: workflows/infrastructure-deployment.md
- Meta-Observer: workflows/meta-observer-pattern.md
- Concepts:
- Philosophy: philosophy.md
- Sovereignty Proof:
- sovereignty-proof/index.md
- 2026-05-15 RPI-leanness reframe: sovereignty-proof/evidence/2026-05-15-rpi-leanness-codex-reframe.md
- 2026-05-16 CDLC F6+F7 findings: sovereignty-proof/evidence/2026-05-16-cdlc-f6-f7-codex-findings.md
- Assurance Profile: assurance-profile.md
- Knowledge Flywheel: knowledge-flywheel.md
- The Science: the-science.md
- CDLC: cdlc.md
- Brownian Ratchet: brownian-ratchet.md
- Context Lifecycle: context-lifecycle.md
- Context Packet: context-packet.md
- Curation Pipeline: curation-pipeline.md
- Evolve Setup: evolve-setup.md
- Local Compute Routing: local-compute-routing.md
- Seed Definition: seed-definition.md
- Scale Without Swarms: scale-without-swarms.md
- Strategic Direction: strategic-direction.md
- Leverage Points: leverage-points.md
- Levels:
- levels/index.md
- L1 — Basics: levels/L1-basics/README.md
- L2 — Persistence: levels/L2-persistence/README.md
- L3 — State Management: levels/L3-state-management/README.md
- L4 — Parallelization: levels/L4-parallelization/README.md
- L5 — Orchestration: levels/L5-orchestration/README.md
- Comparisons:
- comparisons/README.md
- vs SDD: comparisons/vs-sdd.md
- vs GSD: comparisons/vs-gsd.md
- vs Superpowers: comparisons/vs-superpowers.md
- vs Claude-Flow: comparisons/vs-claude-flow.md
- vs Compound Engineer: comparisons/vs-compound-engineer.md
- Convergence:
- convergence/index.md
- The Reading: convergence/the-reading.md
- Ledger: convergence/ledger.md
- Google SRE: convergence/google-sre.md
- Reference:
- reference/index.md
- Glossary: GLOSSARY.md
- Environment Variables: ENV-VARS.md
- Schemas: SCHEMAS.md
- Testing: TESTING.md
- CI/CD: CI-CD.md
- Releasing: RELEASING.md
- Incident Runbook: INCIDENT-RUNBOOK.md
- Troubleshooting: troubleshooting.md
- Agent Footguns: agent-footguns.md
- AgentOps Brief: agentops-brief.md
- AgentOps System Map: agentops-system-map.md
- Reference Deep-Dive: reference.md
- Contracts:
- contracts/index.md
- Repo Execution Profile: contracts/repo-execution-profile.md
- Autodev Program: contracts/autodev-program.md
- RPI Run Registry: contracts/rpi-run-registry.md
- Next-Work Queue: contracts/next-work.schema.md
- Finding Registry: contracts/finding-registry.md
- Finding Compiler: contracts/finding-compiler.md
- Headless Invocation: contracts/headless-invocation-standards.md
- Codex Skill API: contracts/codex-skill-api.md
- Context Assembly Interface: contracts/context-assembly-interface.md
- Session Intelligence Trust Model: contracts/session-intelligence-trust-model.md
- Dream Report: contracts/dream-report.md
- Swarm Evidence: contracts/swarm-evidence.md
- Scope Escape Report: contracts/scope-escape-report.md
- Dispatch Checklist: contracts/dispatch-checklist.md
Reference in New Issue View Git Blame Copy Permalink