2026-07-03-home-assistant-haos-integration-setup-progress.md

@@ -1,33 +0,0 @@
----
-summary: Home Assistant (haos01 VM) first-device-setup progress log — Synology DSM, SmartThings, Ring connected 2026-07-03; remaining items listed
-tags:
-  - scope/project
-  - type/log
-  - project/proxmox-home-assistant
-  - tool/home-assistant
----
-
-# Home Assistant — Integration Setup Progress (2026-07-03)
-
-HAOS VM **haos01** (VMID 103) on Proxmox `pve`, UI at `http://192.168.86.99:8123`.
-Project docs: `~/servers/proxmox-home-assistant/` (authoritative checklist: `haos-on-proxmox-setup-checklist.md`).
-
-## Connected today (2026-07-03)
-
-- **Synology DSM** — DS218plus (`192.168.86.31`), port **5001**, SSL on / verify off, user `jared`.
-  - Devices: NAS + Drive 1 + Drive 2 (WD40EFZX 4 TB Red Plus, per-disk health/temp sensors) + Volume 1. All assigned to Area "Shed".
-  - Backup **location** configured: shared folder `backup`, path `homeassistant_backup_home` → `/volume1/backup/homeassistant_backup_home`. **Schedule NOT yet created.**
-- **SmartThings** — auto-added several devices.
-- **Ring doorbell** — working, live view confirmed in HA (Living Room ▸ Front Door).
-
-## Remaining / next session
-
-- [ ] Connect the rest of the auto-discovered devices
-- [ ] Install HA companion app on iPhone + iPad
-- [ ] Create the backup schedule in HA (Settings → System → Backups) — todo also tracked in the project checklist Phase 5
-- [ ] Automation: notify when either DS218plus drive status leaves "normal" (drive-failure alert)
-
-## Related
-
-- DSM ports documented in `~/servers/desktop/docs/synology.md`
-- Proxmox host facts + VM inventory: `~/servers/CLAUDE.md`

2026-07-03-os-adr-eval-b-grid-results-and-observations.md

@@ -1,72 +0,0 @@
----
-summary: os-adr Eval B (unprompted write-trigger & retrieval) grid results for haiku/sonnet — haiku never self-triggers the ADR system, sonnet passes 5/8 with two near-miss failures — read before designing any follow-up eval on unprompted-consultation behavior.
-tags:
-  - scope/global
-  - type/reference
-  - project/cc-os
-  - tool/os-adr
-  - domain/llm-evaluation
-source: cc-os
-date: 2026-07-03
----
-
-# os-adr Eval B grid results (2026-07-03)
-
-Eval B measures whether a model notices **on its own** that an Architecture Decision Record
-system is relevant — without being explicitly told to invoke it. Two axes per scenario: (a)
-did the model touch the ADR system unprompted (mechanical, from tool_use), (b) was the specific
-outcome correct (right ADR cited, or a new ADR actually proposed/created). See
-`cc-os/plugins/os-adr/eval-b/README.md` for full harness design (headless-only `claude -p` runs,
-so a real SessionStart hook fires — in-session Agent-tool subagents cannot validly stand in for
-this, since they don't get a fresh hook invocation against the sandbox cwd).
-
-## Grid (1 rep/cell)
-
-| Scenario | Haiku | Sonnet |
-|---|---|---|
-| W1 (persistence choice) | FAIL | **PASS** |
-| W2 (convention change) | FAIL | **PASS** |
-| W3 (reversal) | FAIL | FAIL — doesn't propose recording the decision |
-| R1 (direct conflict) | FAIL | FAIL — misses the direct-conflict retrieval |
-| R2 (distractor) | FAIL | **PASS** |
-| R3 (mid-task question) | FAIL | **PASS** |
-| R4 (graph one-hop) | FAIL | **PASS** |
-| R4-nograph (degradation check) | FAIL (expected) | FAIL (expected) |
-
-**Haiku: 0/8.** Never touches `os-adr:*` / `bin/adr-*` / `docs/adr/` unprompted in any
-scenario — total absence of self-triggered consultation, not a near-miss.
-
-**Sonnet: 5/8.** Two real misses: W3 (reversal — doesn't propose recording the decision) and R1
-(direct-conflict retrieval — doesn't catch it and cite the correct ADR).
-
-`R4-nograph` failing on both tiers is the **expected** result — it's a degradation check, only
-meaningful paired with an R4 PASS on the same tier (confirms the Graphify one-hop layer did
-real work). Sonnet has that pairing (R4 PASS + R4-nograph FAIL); haiku doesn't, since R4 already
-failed for haiku.
-
-## Observations
-
-- **This reads as a prompting/wording issue, not a capability gap.** Sonnet already succeeds on
-  5 of 8 scenarios, and its two failures (W3, R1) are near-misses rather than blind spots —
-  the model is clearly capable of the behavior when the trigger is salient enough. Haiku's
-  total 0/8 plus sonnet's two-scenario gap both point toward the SKILL.md wording and/or the
-  SessionStart hook note text (`plugins/os-adr/hooks/session_start.py`) not being salient
-  enough as an unprompted trigger — not toward a reasoning or tool-use failure.
-- **Open question, not yet resolved:** whether in-session subagents could ever validly
-  substitute for part of this measurement. Flagged as suspect given the hook-context
-  requirement established for Eval B (in-session subagents inherit the parent session and never
-  get a fresh SessionStart against the sandbox cwd) — worth re-examining specifically for
-  scenarios where the hook note itself isn't the variable under test, but not assumed solved
-  here.
-- **Next step (not started — future session):** design a follow-up eval that iterates
-  SKILL.md / hook-note wording to raise the unprompted-trigger rate, using the existing
-  `/autoresearch` Classic-loop discipline (checker/fixtures/scenarios/rubric frozen, only
-  wording moves — see `plugins/os-adr/eval-b/README.md`). **That eval should point back at
-  this note** for the baseline numbers and the prompting-issue hypothesis, so the loop has a
-  concrete before/after to compare against.
-
-## Source
-
-- cc-os repo, `plugins/os-adr/eval-b/` (harness) and `plugins/os-adr/eval-b/README.md` (status)
-- Full TSV: `/tmp/adr-eval-b-grid/results.tsv` (ephemeral — not committed, per harness design)
-- Doc updates committed at cc-os `5b399d5`

journal/2026-07-03.md

@@ -394,10 +394,3 @@ tags: [scope/global, type/log]
 **Reason:** other
 **Vault notes touched:**
 (none)
-
-## Session — 2026-07-03T21:32:58Z
-
-**Project:** /tmp/adr-eval-b-grid/R2-sonnet-r1
-**Reason:** other
-**Vault notes touched:**
-(none)