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>
