night-shift: issue templates + fix stale test-count badge (#3)

Closes Tier 3 item 17 (aliased with Tier 9 item 82). README/CONTRIBUTING/CI
badge were already in place from an earlier pass; the remaining 9b gap was
.github/ISSUE_TEMPLATE/ (bug + feature). Also fixes the test-count badge and
Tests section, stale at 100 since a Windows VectorStore.close() fix grew the
suite to 107 (per the 2026-07-14 NIGHT_SHIFT.md entry).

Verified: pytest tests/ -q, 107/107 passed offline, no API key needed.
Docs-only diff, no application code touched.

Co-authored-by: Claude <noreply@anthropic.com>

Author: zaidwhy

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,29 @@
+---
+name: Bug report
+about: Something in Personal LLM doesn't work as expected
+title: "[Bug] "
+labels: bug
+assignees: ''
+---
+
+**Describe the bug**
+A clear description of what went wrong.
+
+**To reproduce**
+Steps to reproduce (which command: `ingest`, `ask`, `agent`, `review`, etc.):
+```
+& "venv\Scripts\python" -m personal_llm.interfaces.cli ...
+```
+
+**Expected behavior**
+What you expected to happen instead.
+
+**Environment**
+- OS:
+- Python version (must be 3.12, `python --version`):
+- Personal LLM commit/version:
+- Model provider in use (Gemini / Ollama):
+
+**Additional context**
+Logs, stack traces, or anything else relevant. Redact any memory content, API keys, or
+tokens before pasting.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,21 @@
+---
+name: Feature request
+about: Suggest an idea for Personal LLM
+title: "[Feature] "
+labels: enhancement
+assignees: ''
+---
+
+**What problem would this solve?**
+A clear description of the gap or friction you're hitting.
+
+**Proposed solution**
+What you'd like to see happen. Note which layer it touches - engine (`src/personal_llm/`)
+vs. an interface (CLI/FastAPI/Streamlit); see [CONTRIBUTING.md](../../CONTRIBUTING.md)
+ground rule 4 (interfaces stay thin, logic belongs in the engine).
+
+**Alternatives considered**
+Any other approaches you thought about.
+
+**Additional context**
+Anything else relevant (related ADRs in `docs/DECISIONS/`, related issues, links).

README.md

@@ -1,7 +1,7 @@
 # Personal LLM
 
 [![CI](https://github.com/syzayd/personal-llm/actions/workflows/ci.yml/badge.svg)](https://github.com/syzayd/personal-llm/actions/workflows/ci.yml)
-![Tests](https://img.shields.io/badge/tests-100%20passed%20offline-brightgreen)
+![Tests](https://img.shields.io/badge/tests-107%20passed%20offline-brightgreen)
 ![Python](https://img.shields.io/badge/python-3.12-blue)
 [![License: MIT](https://img.shields.io/badge/license-MIT-green)](LICENSE)
 
@@ -107,7 +107,7 @@ under 5 minutes with no API key.
 ```powershell
 & "venv\Scripts\python" -m pytest tests/ -q
 ```
-100 tests, fully mocked - no API key, network, real model, or real Tesseract binary
+107 tests, fully mocked - no API key, network, real model, or real Tesseract binary
 required. CI runs this on every push (keyless by design).
 
 ## Architecture at a glance