sync: auto-sync from HOWARD-HOME at 2026-04-23 06:21:23

Author: Howard Enos
Machine: HOWARD-HOME
Timestamp: 2026-04-23 06:21:23
This commit is contained in:
2026-04-23 06:21:24 -07:00
parent abfb0a18b0
commit 7e2e3a5882
5 changed files with 118 additions and 18 deletions

View File

@@ -12,15 +12,31 @@ Ollama runs on Mike's workstation (DESKTOP-0O8A1RL) with GPU acceleration. Avail
## Endpoints
- **DESKTOP-0O8A1RL** (local): `http://localhost:11434`
- **Any other machine** (Tailscale required): `http://100.92.127.64:11434`
Auto-detect: any machine that has a local Ollama listening on `127.0.0.1:11434` uses local. Otherwise fall back to Mike's workstation over Tailscale.
```bash
# Preferred universal resolver — works on any machine
if curl -s -m 2 http://localhost:11434/api/tags >/dev/null 2>&1; then
OLLAMA="http://localhost:11434"
else
OLLAMA="http://100.92.127.64:11434"
fi
```
Rationale:
- **Mike's workstation (DESKTOP-0O8A1RL):** local matches, no change.
- **HOWARD-HOME:** also has a local Ollama with the canonical model set (confirmed 2026-04-22). Uses local — faster, zero Tailscale hop, no load on Mike's GPU.
- **Other team machines:** no local Ollama → falls back to Mike's over Tailscale.
- **Mike's machine offline:** graceful degradation — local users continue working; non-local users get a clean timeout.
Manual override (for testing or explicit preference): set `OLLAMA=http://100.92.127.64:11434` before the call.
Check reachability:
```bash
curl -s http://100.92.127.64:11434/api/tags | jq -r '.models[].name'
curl -s $OLLAMA/api/tags | jq -r '.models[].name'
```
If it fails: verify Tailscale is connected (`tailscale status`) and Mike's workstation is online.
If neither endpoint responds: verify Tailscale (`tailscale status`) and whether your local Ollama service is running.
## Access Control
@@ -30,24 +46,29 @@ If it fails: verify Tailscale is connected (`tailscale status`) and Mike's works
## Calling Ollama
Resolve endpoint from identity.json first:
```bash
OLLAMA=$([ "$(jq -r .machine .claude/identity.json 2>/dev/null)" = "DESKTOP-0O8A1RL" ] \
&& echo "http://localhost:11434" || echo "http://100.92.127.64:11434")
```
Use the `/api/chat` endpoint with `think:false` for qwen3 models. The older `/api/generate` endpoint on qwen3 puts output into thinking tokens that don't appear in the `response` field — you'll get an empty response if you use `/api/generate`.
Preferred one-liner (avoids shell escaping):
Preferred one-liner:
```bash
py -c "
import urllib.request, json, sys
url = 'http://localhost:11434/api/generate'
body = json.dumps({'model':'qwen3:14b','prompt': sys.argv[1],'stream':False}).encode()
res = json.loads(urllib.request.urlopen(urllib.request.Request(url, body)).read())
print(res['response'])
python -c "
import urllib.request, json, sys, os
OLLAMA = os.environ.get('OLLAMA') or ('http://localhost:11434' if __import__('urllib.request').request.urlopen(urllib.request.Request('http://localhost:11434/api/tags'),timeout=2) else 'http://100.92.127.64:11434')
body = json.dumps({
'model':'qwen3:14b',
'messages':[{'role':'user','content': sys.argv[1]}],
'stream':False,
'think':False
}).encode()
res = json.loads(urllib.request.urlopen(urllib.request.Request(OLLAMA+'/api/chat', body), timeout=120).read())
print(res['message']['content'])
" "Your prompt here"
```
For code suggestions, swap `qwen3:14b` for `codestral:22b`.
Or set `$OLLAMA` once from bash (see auto-detect formula above) and reuse it across calls.
For code suggestions, swap `qwen3:14b` for `codestral:22b`. Codestral doesn't need `think:false`.
Cold-start is ~30-50s on first call per model per session. Warm calls are 1-5s.
## When to Use Which Model

View File

@@ -23,6 +23,7 @@
- [D2TESTNAS SSH Access](feedback_d2testnas_ssh.md) - Use root@192.168.0.9 with Paper123!@#, not sysadmin
- [Bypass Permissions Setting](feedback_bypass_permissions_setting.md) - Set permissions.defaultMode to bypassPermissions in settings.json on all machines
- [365 Remediation Tool](feedback_365_remediation_tool.md) - Always means Graph API app fabb3421, not CIPP
- [Ollama Tier-0 Routing](feedback_ollama_tier0_routing.md) - Route drafts/summaries/classifications through Ollama (qwen3:14b). Mike designed ClaudeTools this way — not optional.
## Machine
- [ACG-5070 Workstation Setup](reference_workstation_setup.md) - Windows 11 Pro clean install 2026-03-30, replaced CachyOS. All tools installed.

View File

@@ -0,0 +1,46 @@
---
name: Route Tier-0 tasks through Ollama (Mike's ClaudeTools design intent)
description: Drafts, summaries, classifications, extractions MUST go through Ollama per Mike's tiered-model architecture. Don't default to Claude inference for low-stakes text generation.
type: feedback
---
Route Tier-0 tasks (summaries, classifications, drafts, extractions) through Ollama. Not optional — this is how Mike designed ClaudeTools to work.
**Why:** Mike built the tiered-model architecture (`CLAUDE.md` Model Routing section + `.claude/OLLAMA.md`) deliberately. Tier 0 is free + fast + private. Defaulting to Claude for every drafting task burns context window and Anthropic tokens on work that qwen3:14b does fine.
**How to apply:**
- Drafting emails, session-log paragraphs, status-update sentences, commit-message first-drafts → qwen3:14b
- Summarizing long output (Graph JSON, PowerShell transcripts, log tails) → qwen3:14b
- Extracting structured data from text → qwen3:14b
- Suggesting refactors / generating docstrings → codestral:22b (then review)
- NEVER for: auth decisions, credential handling, production migrations, security review, citation work, production-change scripts
**Endpoint resolution (updated 2026-04-22 in `.claude/OLLAMA.md`):**
```bash
if curl -s -m 2 http://localhost:11434/api/tags >/dev/null 2>&1; then
OLLAMA="http://localhost:11434"
else
OLLAMA="http://100.92.127.64:11434"
fi
```
HOWARD-HOME has the canonical models loaded locally (qwen3:14b, codestral:22b, nomic-embed-text, plus bonus qwen3-coder:30b) — so HOWARD-HOME uses local Ollama, not Mike's. Zero Tailscale hop.
**Call pattern for qwen3 — use `/api/chat` with `think:false`**, NOT `/api/generate`. qwen3 on generate endpoint dumps reasoning into internal thinking tokens and returns empty `response` field. Chat endpoint with `think:false` returns clean content in `message.content`:
```python
body = json.dumps({
'model':'qwen3:14b',
'messages':[{'role':'user','content': prompt}],
'stream':False,
'think':False
}).encode()
# POST to OLLAMA + '/api/chat'
# Read res['message']['content']
```
Codestral doesn't need `think:false` — just use it on `/api/chat` normally.
Cold-start ~30-50s on first call per model per session; warm calls 1-5s.
**Incident 2026-04-22:** Spent an entire Cascades rollout session (G1 hygiene, orphan cleanup, risk register, synology discovery, etc.) without routing a single task through Ollama despite many drafting opportunities (report drafts, summary text, email drafts). Howard called this out: "just make sure ollama is being used as mike has designed claudetools to work."