Drive 2 (label "Backup", 12 TB, 6.77 TB used) — second of N VWP
backup drives. Scanned via WizTree, analyzed with analyze_wiztree.py.
NEW source content:
- 000_ASource/ — Darv's active work-in-progress folder. Contains
TEST_VWP.vbp (2021-08-16, only .vbp newer than the 2020-06-09 baseline),
four frmLotInfo*.frm variants (2020-10 to 2021-08), and an
MSSCCPRJ.SCC file confirming Darv used Visual SourceSafe.
- The accompanying Vwp.mdb (2022-10-19, 764 MB) stays on local disk
per .gitignore — newest database snapshot we have.
Analysis CSVs:
- source-analysis/drive2-2026-05-16/ — per-category + per-keyword
breakdown of drive 2's 3.95M files (vs drive 1's 1.87M). Categories
largely match drive 1 but with ~2x volume.
Net findings vs drive 1:
- Confirmed 4-year gap: only 4 .vbp files newer than 2020-06-09 on
drive 2, all the same TEST_VWP.vbp scaffold. Main ORDERS_C.vbp source
remains 2020-06-09. Darv stopped active VB6 dev around mid-2020.
- 43 GB Win7 Backup-and-Restore set in D:\Archive\Darv-Win7-PC\ (2023)
not copied — deferred to later drives, ZIPs extractable on demand.
- Master Darv folder is bit-for-bit duplicate of drive 1's master (135 GB,
same file/folder counts). Skipped.
New helper scripts:
- find_newer_vbp.py — list .vbp files newer than a date, filter SDK noise
- drive2_inspect.py / drive2_priorities.py — drive-specific triage
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Recovered Darv's VB6 source for the Valley Wide Plastering Orders
application from the D: backup drive (label "Backup", 8 TB, 5.3 TB used).
This is the first time we've had the actual source — prior session only
had a single frmPayroll.frm from the AD server.
Three project variants identified across two snapshots:
- Full-Project/ (2,129 files, 124 MB) — D:\Office-Estimates\Darv\Full\Project\
- Kingston-Project/ (2,189 files, 130 MB) — D:\Office-Estimates\Darv\Kingston\Project\
- Source/ (170 files, 559 MB) — D:\Office-Estimates\Darv\Source\ wholesale
- SOURCE-HOLD/ (3 files, 1 MB) — D:\Office-Estimates\Darv\SOURCE HOLD\
Latest ORDERS_C.vbp date is 2020-06-09 (Kingston snapshot). Production
Orders_10A.exe was live as of April 2024 — open question whether newer
source exists on other backup drives Mike will scan next.
Also includes per-category and per-keyword analysis CSVs from a WizTree
file-list export, plus the analyzer script that produced them
(re-runnable for the next drive's CSV).
VMs (VWIN7-DW.vdi 8.3 GB + XP-for-ORDERS_copy.vdi 2.8 GB), the live
VWP.mdb, and the 393 MB raw WizTree CSV stay on disk only — gitignored.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
tmp_qwen_reason.py, tmp_qwen_test.py, tmp_qwen_test2.py — additional
local qwen test scratch from today's benchmarking work. The routing
decisions live in OLLAMA.md; the throwaway scripts don't need to ship.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Removes tmp_bench_8b.py, tmp_hw_check.ps1, and tmp_ollama_bench.py
from DESKTOP-0O8A1RL's qwen3:8b benchmark. The routing decisions and
numbers are captured in OLLAMA.md; the scripts were one-off scratch
work and don't need to live in the repo.
Untracked counterparts on GURU-BEAST-ROG (benchmark_qwen_3_6.py,
rescore_qwen.py, qwen-benchmark-2026-05-16.{md,json}) were also
removed locally.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The qwen3:8b routing update inserted footnote lines mid-table in both
the "What Ollama owns" and "When to Use Which Model" sections, splitting
each table in half so renderers treated the qwen3.6 rows as paragraph
text. Moved footnotes below the closing table row in both places.
Also updated the bottom "Rule of thumb" line: previously named qwen3:14b
with a "2x faster" claim that's now stale on DESKTOP-0O8A1RL where 8b is
the prose model. Generalized to "the per-machine prose model".
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Benchmarked qwen3.6 (36B MoE) vs qwen3:14b and qwen3:32b on 16
representative prompts. qwen3.6 scored 15/16 vs 14b 11/16 and 32b
12/16, winning every strict-format/adherence test (multi-step rules,
weekend-aware scheduling, prompt-injection resistance, word-limit
summary). Single reasoning regression noted for re-check at qwen3.7.
Updated .claude/OLLAMA.md (Models, Documentation Engine, and
When-to-Use tables) and .claude/CLAUDE.md one-line model summary to
route strict-format work to qwen3.6 and keep bulk prose on qwen3:14b
(2x faster). Also removed openclaw npm package + ~/.openclaw data dir
earlier in the session.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- CODING_GUIDELINES.md: tighten parity rule wording to match Mike's intent:
"add feature X" means Windows + Linux + macOS in the same commit
- memory: add feedback_gururmm_agent_parity for future session enforcement
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Hook was querying only to_session=HOSTNAME/claude-main, missing messages
addressed to the short alias (e.g. "howard"). Now reads identity.json for
the alias and queries both, merging results before display.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Gap #13 in hipaa.md marked resolved. Same update in hipaa-caregiver-controls.md and m365.md.
Confirmed 2026-05-14: no separate HIPAA BAA acceptance exists or is required for M365 Business
plan tenants under the Microsoft Customer Agreement.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Full tenant verification sweep: all Intune/Entra objects match session logs
- Entra Connect staging mode exited; 17 AD groups synced to cloud
- CA policies (Block-off-network, Sign-in-frequency-8h, Block-non-compliant) patched from SG-Caregivers-Pilot to AD-synced SG-Caregivers
- Registration Campaign exclusion updated to SG-Caregivers
- Deleted test accounts: howard.enos (AD) and pilot.test (M365)
- Documented Christine Nyanzunda collision risk, Ederick Yuzon open item, standing security-group rule
- Session log written
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
