tryassay 0.21.1 → 0.22.0

package/README.md

@@ -211,7 +211,7 @@ export ANTHROPIC_API_KEY="sk-ant-..."
 npm install -g tryassay
 export ANTHROPIC_API_KEY="sk-ant-..."
 
-# Generate code with Layer 2 verification built in
+# Generate code with built-in claim verification
 tryassay generate --task "Write a function that validates email addresses" --lang typescript --verbose
 ```
 
@@ -301,7 +301,7 @@ const check = await sdk.verify({
 // check.verifications: each claim's verdict (PASS/PARTIAL/FAIL)
 ```
 
-The SDK enforces Layer 2 — `generate()` always returns a verification proof alongside the code. The formal verifier runs deterministic pattern checks (regex, not LLM) and can override LLM verdicts. On its first production call, it caught the LLM hallucinating PASS on code with SQL injection.
+The SDK enforces verification — `generate()` always returns a verification proof alongside the code. The formal verifier runs deterministic pattern checks (regex, not LLM) and can override LLM verdicts. On its first production call, it caught the LLM hallucinating PASS on code with SQL injection.
 
 ---
 
@@ -352,7 +352,7 @@ Two modes: **Assay API** (recommended, uses your Assay key) or **BYOK** (bring y
 
 | Command | Description |
 |---------|-------------|
-| `tryassay generate` | Generate verified code — Layer 2 verification below the model call |
+| `tryassay generate` | Generate verified code — claim verification below the model call |
 | `tryassay assess <target>` | Run autonomous LVR assessment against a codebase or GitHub URL |
 | `tryassay init` | Initialize project configuration |
 | `tryassay hallucinate` | Generate a hallucinated ToS/API docs/user manual |
@@ -557,7 +557,7 @@ A complete 6-iteration cycle that achieves 90%+ compliance costs approximately *
 Contributions are welcome. Areas where help is particularly valuable:
 
 - **Multi-document hallucination** -- Extending beyond ToS to API docs, user manuals, privacy policies, and compliance certifications simultaneously
-- **Formal verification integration** -- Replacing LLM-based verification with property-based testing, model checking, or static analysis for specific claim categories
+- **Deterministic verification integration** -- Replacing LLM-based verification with property-based testing, model checking, or static analysis for specific claim categories
 - **CI/CD integration** -- Running Assay in continuous integration pipelines for specification-drift detection
 - **Language support** -- The CLI currently targets TypeScript/JavaScript codebases; other languages need codebase indexing adapters
 - **Benchmarking** -- Comparing initial hallucination quality across different LLMs (Claude, GPT-4, Gemini, Llama)

package/demo/.claude/.truth_last_prompt

@@ -0,0 +1 @@
+1771956016.3584828

package/demo/.claude/truth_status

@@ -0,0 +1 @@
+green