From 7ed43fcb594246860eb571f4cfe9ff45702f2784 Mon Sep 17 00:00:00 2001 From: Keysat Date: Mon, 15 Jun 2026 17:29:47 -0500 Subject: [PATCH] Mark ROADMAP item 7 (placement guide) done; refresh Current state --- AGENTS.md | 37 +++++++++++++++++++++---------------- ROADMAP.md | 26 ++++++++++---------------- 2 files changed, 31 insertions(+), 32 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index 6b56830..2a404db 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -92,7 +92,7 @@ should carry this so any vendor's agent surfaces pending items at session start: in `adapters/claude/`, symlinked into `~/.claude`). The repo dogfoods its own standard: inbox-check line, deny-by-default `.gitignore`, relative symlinks, capture→triage→roadmap loop. - `/roundup` writes a tracked `STATUS.md` snapshot each run (overwritten, committed + pushed — - diffable over time); latest snapshot dated 2026-06-14. + diffable over time); latest snapshot dated 2026-06-15. - `/new-project` is the inverse of `/retrofit`: workshops a captured `(new)` idea into a standards-compliant repo and publishes to Gitea via a manual-create gate; the stack quality gate is deferred to a future `/harden`. Now carries a **form-factor gate** (is this even a @@ -101,10 +101,12 @@ should carry this so any vendor's agent surfaces pending items at session start: **placement** step that walks `guides/placement.md`, the falsifiable-exit "substance rule," and a posture section — all harvested from a retired `idea-workshop` skill. A new project's architectural decisions live in its `AGENTS.md` `## Decisions` section (no separate ADR file). -- `guides/placement.md` is a new shared reference (where a project should run / which model / - what data layer), ported from that skill. **Its infra facts are UNVERIFIED** — generated - one-shot from chat history — and need a review pass with me (ROADMAP item 7); the file and - `how-i-work.md` both flag this. +- `guides/placement.md` is a shared reference (where a project should run / which model / + what data layer). **Its infra facts were verified with me 2026-06-15** (ROADMAP item 7 done): + x86 StartOS 0.4.0 box + full service list; the two-Spark role split (LLM vs audio/speech, + Qdrant on the audio Spark, matrix-bridge hosted there); route via the Spark Control gateway + and query the active model rather than hardcoding one; LAN/WireGuard/StartTunnel networking. + UNVERIFIED banner dropped. - **The upgraded `/new-project` flow has had its first live end-to-end run** — scaffolded `~/Projects/matrix-bridge` (a Matrix→Claude Code bridge bot) from a prior scoping package, folding its SPEC/DECISIONS into the new AGENTS.md `## Decisions` scheme. @@ -113,14 +115,17 @@ should carry this so any vendor's agent surfaces pending items at session start: - Cross-repo git-hygiene audit done: 9 repos audited, no leaks, 6 remediated + pushed; the canonical `.claude/` block is now **deny-by-default** (in `portability.md`; full detail in git log + ROADMAP item 6). -- Last session: corrected a stale repo name (`Workout-log` → `proof-of-work`) across - `STATUS.md`/`ROADMAP.md` after a reviewer pass, and deleted the dead non-git `Workout-log` - folder (crash logs only). Nothing in progress — committed and pushed; tree clean. -- **Next steps:** (1) verify & correct `guides/placement.md`'s infra facts with me (ROADMAP - item 7 — cheap, unblocks trustworthy placement in `/new-project`); (2) the cross-repo - quality-gate standard + `/harden` (ROADMAP item 1 — also unblocks `/new-project`'s deferred - quality-gate step); (3) the non-git-folder sweep under `~/Projects` (item-6 residual; - `Workout-log` cleared, count now ~14). -- Queued elsewhere / specced-not-built: the `ten31-transcripts` mini-retrofit waits in - `INBOX.md` for that repo's `/triage`; the SessionStart hook (item 3) and inbox-line bootstrap - threading (item 4) remain on the ROADMAP. +- This session: ran `/roundup` (STATUS.md snapshot 2026-06-15); verified & corrected + `guides/placement.md` with me and committed it (ROADMAP item 7 done); captured a + `(ten31-database)` networking-doc fix to `INBOX.md`. **Paused mid-task:** a `how-i-work.md` + consolidation pass — analysis is done (promote 3 gap rules: instruction-file structure, + verify-by-running, sensitive-data-stays-local; plus a selective trim of now-global + duplicates from repo AGENTS.md files) and awaits my go-ahead before any edits. +- **Next steps:** (1) decide the paused `how-i-work.md` consolidation (which of the 3 gap + rules to promote; how aggressive to trim repos given the self-containment tradeoff); (2) the + cross-repo quality-gate standard + `/harden` (ROADMAP item 1 — also unblocks `/new-project`'s + deferred quality-gate step); (3) the non-git-folder sweep under `~/Projects` (item-6 residual; + count ~13). +- Queued elsewhere / specced-not-built: the `ten31-transcripts` mini-retrofit and a new + `(ten31-database)` networking-doc fix wait in `INBOX.md` for those repos' `/triage`; the + SessionStart hook (item 3) and inbox-line bootstrap threading (item 4) remain on the ROADMAP. diff --git a/ROADMAP.md b/ROADMAP.md index b8bb7ab..bae92fe 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -131,20 +131,14 @@ allow-by-default and would have *un-ignored* `premier-gunner`'s password-bearing "scratch, don't track" decision. - **`start-os`** is an external upstream (Start9Labs/start-os) — out of scope, no action. -## 7. Verify & correct the placement guide +## 7. Verify & correct the placement guide ✅ DONE (2026-06-15) -**Why:** `guides/placement.md` was ported from a one-shot `idea-workshop` skill that was -generated from chat history and **never verified** against the actual setup. Its *decision -sequence* and *substance rule* are sound; its **infrastructure facts** (Start9 services, -Spark/Qwen3 model lineup, embeddings/TTS, network/access, data-layer defaults) are -provisional and almost certainly need correcting. The file carries an "UNVERIFIED" banner -pointing here until that's done. - -**What it touches if wrong:** `/new-project` (Phase 2 walks it for placement) and -`how-i-work.md` (one-line pointer), so stale facts propagate into every new repo's placement -decision. Worth a focused pass. - -**To do:** walk the "Infrastructure facts" section with the user section by section — confirm -or correct each (running Start9 services, the Spark gateway endpoint + Qwen3 details, TTS/ -embeddings, WireGuard/iOS access, data-layer defaults) — then drop the UNVERIFIED banner and -update the "last generated" line to a real "last verified" date. +Walked the "Infrastructure facts" section with the owner and corrected it against the real +setup (cross-checked against the project repos + a Spark-control topology dump). Fixes: **x86** +StartOS **0.4.0** box + full service inventory (Gitea, Nextcloud, Home Assistant, CLN + RTL, +Open WebUI, Vaultwarden, Synapse, and every Claude-built app); the two-Spark **role split** +(LLM Spark = vLLM; audio/speech Spark = Parakeet / Kokoro / Sortformer + TitaNet + bge-m3 + +Qdrant, and it hosts matrix-bridge); **don't hardcode a model — query the Spark Control +gateway** for the live one (daily driver Qwen3.6, hot-swappable); networking reduced to LAN / +WireGuard / StartTunnel (Proton VPN + Tor were legacy, dropped). UNVERIFIED banner replaced +with a "verified 2026-06-15" note; decision steps 4 and 6 aligned. Commit `ee5c8bb`.