vikingowl
5170c73dac
Top-level docs were stale and the .gitea/ issue templates referenced a workflow that is no longer in use. - README: rewrite around the current feature set (SLM routing, profiles, plugin TOFU, SafeProvider boundary, current model defaults). Add a pre-built-binary install section plus Docker (ghcr.io) install path for users without a Go toolchain. Document the GitHub mirror. - CONTRIBUTING: drop the dead issue-template reference, note Gitea upstream + GitHub mirror split, expand the package map and test-target table. - AGENTS: rebuild as a domain glossary (Elf / Arm / Turn / SafeProvider / Incognito / Profile) plus non-obvious conventions an outside agent needs and would not infer from the code. - TODO: trim completed waves into a History section, fix a broken link to the never-written Wave 3 plan file, surface active backlog. - docs/essentials/INDEX: add ADR-004 (PostToolUse hook ordering) to the ADR list. - LICENSE + NOTICE: adopt Apache License 2.0. Patent grant matters because gnoma bundles SDKs from Anthropic / OpenAI / Google / Mistral and ships derivative tooling that runs untrusted MCP servers. - Delete .gitea/issue_template/ and gemma-integration-analysis.md (latter is obsolete per its own preamble — Node.js-specific notes that don't apply to the Go implementation).
2.4 KiB
2.4 KiB
Gnoma — TODO
Active work, newest first.
In flight
- Distribution —
.goreleaser.ymlis configured forlinux/darwin/windows×amd64/arm64. Still pending: first tag + release pipeline trigger, optional Homebrew tap and Docker image, mirror release publishing to GitHub. - Compound tools (post-SLM Phase E) — held until ≥50 SLM
observations inform which primitives are worth adding. See
docs/superpowers/plans/2026-05-19-post-slm-unlock.md.
Stable backlog (not in active phases)
- Thinking mode (disabled / budget / adaptive) — M12.
- Structured output with JSON schema validation — M12.
- Native agy JSON output — switch the subprocess provider to
--output-format stream-jsononce the agy CLI supports it, replacing the current prompt-augmentation fallback. - SQLite session persistence + serve mode — M10.
- Task learning (pattern recognition, persistent tasks) — M11.
- Web UI (
gnoma web) — M15. - OAuth / keyring — M13.
- Observability (feature flags, cost dashboards) — M14.
- PE / Mach-O ELF support — future, after ELF Phase 6.
History
Completed initiatives, kept here as pointers to their plan files:
- Post-audit security hardening — complete 2026-05-19. Three waves
- one ADR closed all 14 findings from the external review:
- Wave 1 — SafeProvider boundary
- Wave 2 — Incognito coherence
- Wave 3 — scanner + path hygiene (rolled out directly without a
plan file; see commits leading up to 2026-05-19 on
internal/security) - ADR-004 — PostToolUse hook ordering
- Post-SLM unlock — plan. Phases A–D complete (two-stage tool routing, CLI agent binary override, user profiles, per-arm capability tags).
- 2026-05-07 roadmap — plan. M1–M8 done; SLM classifier (Phase 3) complete; Phase 4 superseded by the post-SLM plan.
Reference
- Milestones:
docs/essentials/milestones.md - Decisions:
docs/essentials/decisions/ - ADR-002 (SLM routing, supersedes earlier ADR-009):
docs/essentials/decisions/002-slm-routing.md