stilltrue 0.3.0 → 0.4.0

package/README.md

@@ -9,9 +9,14 @@ no server, no dashboard, no SaaS.
 
 | Command | Watchdog | Status |
 |---|---|---|
-| `npx stilltrue drift` | Curated facts vs their live authoritative sources — fails the build on rot | **v0.1 focus** |
-| `npx stilltrue golden` | Deterministic regression evals for answers | later (may wrap promptfoo) |
-| `verify` (library) | Staged acceptance pipeline for AI output — judge answers against sources in the request path | **shipped 0.3.0** |
+| `npx stilltrue drift` | Curated facts vs their live authoritative sources — fails the build on rot | shipped |
+| `npx stilltrue report` | Self-contained HTML drift timeline from recorded runs | shipped |
+| `verify` (library) | Staged acceptance pipeline for AI output — judge answers against sources in the request path | shipped |
+
+For golden-style regression evals (did a code change break an answer?), use
+[promptfoo](https://promptfoo.dev) — **promptfoo tests your prompts;
+stilltrue tests your facts.** Our eval doctrine and how the tools pair:
+[docs/GOLDEN.md](docs/GOLDEN.md).
 
 **Why drift first:** "drift detection" in the market means statistical ML
 feature drift; website-change monitors alert humans, not CI. Nobody ships
@@ -97,9 +102,10 @@ const gen = await generateVerified({ generate: (feedback) => ask(model, prompt,
 
 ## Status
 
-v0.3 — `drift` and `report` running in production CI (AskGwinnett); `verify`
-shipped as a library. `golden` remains open: wrap promptfoo or defer to it
-(see the brief's competitive research).
+v0.4 — feature-complete for the 1.0 shape: `drift` and `report` run in
+production CI (AskGwinnett), `verify` runs in the production request path
+(AskGwinnett's pre-publish check sweep). Golden is deliberately out of
+scope — settled in [docs/GOLDEN.md](docs/GOLDEN.md).
 
 ## License
 

package/dist/cli.js

@@ -95,7 +95,8 @@ try {
             process.exit(await report(rest));
             break;
         case 'golden':
-            console.error('stilltrue golden: not implemented yet — drift shipped first (docs/BRIEF.md)');
+            console.error('stilltrue deliberately has no golden runner — promptfoo tests your prompts; stilltrue tests your facts.\n' +
+                'Use https://promptfoo.dev for prompt/answer regression evals. Doctrine + pairing guide: docs/GOLDEN.md');
             process.exit(1);
             break;
         default:

package/dist/config.d.ts

@@ -58,8 +58,6 @@ export interface StilltrueConfig {
     drift?: DriftCheck<any, any>[];
     /** Named verify pipelines (see src/verify.ts) — usable from library code. */
     verify?: Record<string, import('./verify.ts').VerifyStage<any>[]>;
-    /** golden is a later phase — see docs/BRIEF.md build plan. */
-    golden?: unknown;
 }
 /** Identity function for typed configs: `export default defineStilltrue({...})`. */
 export declare function defineStilltrue(config: StilltrueConfig): StilltrueConfig;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "stilltrue",
-  "version": "0.3.0",
+  "version": "0.4.0",
   "description": "Your tests check your code. stilltrue checks your facts. CI checks for AI-in-the-loop apps: drift (curated facts vs live sources), golden (regression evals), verify (judge answers against sources).",
   "keywords": [
     "drift",