feat: add long-session quality test (Issue #12)

50-turn multi-phase conversation test that detects quality degradation
under sustained context pressure. Supports Ollama and llama-server
backends with KV cache type configuration.

Phases: code_gen -> debug -> refactor -> test -> iterate
Metrics: quality score, coherence drift, hallucinated references,
repetition ratio, prompt relevance.

Includes --compare mode for side-by-side KV type comparison.
Acceptance: run on both TurboQuant and FP16, compare results.

.gitea/workflows/smoke.yml

@@ -13,12 +13,12 @@ jobs:
           python-version: '3.11'
       - name: Parse check
         run: |
-          find . -name '*.yml' -o -name '*.yaml' | grep -v .gitea | grep -v llama-cpp-fork | xargs -r python3 -c "import sys,yaml; [yaml.safe_load(open(f)) for f in sys.argv[1:]]"
-          find . -name '*.json' | grep -v llama-cpp-fork | while read f; do python3 -m json.tool "$f" > /dev/null || exit 1; done
-          find . -name '*.py' | grep -v llama-cpp-fork | xargs -r python3 -m py_compile
+          find . -name '*.yml' -o -name '*.yaml' | grep -v .gitea | xargs -r python3 -c "import sys,yaml; [yaml.safe_load(open(f)) for f in sys.argv[1:]]"
+          find . -name '*.json' | xargs -r python3 -m json.tool > /dev/null
+          find . -name '*.py' | xargs -r python3 -m py_compile
           find . -name '*.sh' | xargs -r bash -n
           echo "PASS: All files parse"
       - name: Secret scan
         run: |
-          if grep -rE 'sk-or-|sk-ant-|ghp_|AKIA' . --include='*.yml' --include='*.py' --include='*.sh' 2>/dev/null | grep -v .gitea | grep -v llama-cpp-fork; then exit 1; fi
+          if grep -rE 'sk-or-|sk-ant-|ghp_|AKIA' . --include='*.yml' --include='*.py' --include='*.sh' 2>/dev/null | grep -v .gitea; then exit 1; fi
           echo "PASS: No secrets"

benchmarks/run_benchmarks.py

@@ -5,16 +5,8 @@ TurboQuant Benchmarking Suite — Multi-Backend (Issue #29)
 Supports Ollama and llama-server backends with KV cache type configuration.
 Measures: TTFT, tokens/sec, latency, peak memory.
 
-IMPORTANT — Perplexity Limitation (Issue #63):
-  Ollama does NOT expose token logprobs. This means:
-  - True perplexity (PPL) cannot be measured via the Ollama backend
-  - The metrics here (tok/s, latency) are throughput proxies, not quality gates
-  - For real perplexity measurement, use benchmarks/run_perplexity.py
-    which calls llama-perplexity directly (--logprobs support)
-  - The pass criterion "PPL delta <= 0.5" cannot be validated via Ollama
-
 Usage:
-    # Ollama (default) — throughput benchmarks only, NOT perplexity
+    # Ollama (default)
     python3 benchmarks/run_benchmarks.py --backend ollama --model llama3
 
     # llama-server with turbo4 KV