@inference/fast 0.0.38 → 0.0.40-beta.89

package/README.md

@@ -75,3 +75,60 @@ bun run dev -- login
 
 The dashboard and inference URLs are derived automatically from a localhost
 relay unless explicitly overridden.
+
+## Testing integrations
+
+Three suites cover the harness integrations:
+
+- `bun run test:integration` — hermetic; spawns the CLI against a local mock
+  gateway and asserts the exact config every harness writes (all Claude slots,
+  pickers, per-agent models, byte-exact `off` restore), plus drift between the
+  shipped harnesses and the fast website's integration list. Runs in PR CI via
+  `ci:build-and-verify`.
+- `bun run test:e2e` (`tests/auth-flow/`) — the full auth flow against the
+  LOCAL stack: a fresh account signs up, the CLI does the real device-code
+  login (the test approves the code server-side, no browser), the relay mints
+  a machine key through tRPC, and `fast <harness> on` writes config; `logout`
+  restores and the disabled key is proven rejected by the gateway. Runs in the
+  e2e harness (`[inference] fast-cli auth-flow e2e` job). Needs the local stack
+  (`task run-test-harness-headless`) on current code — the CLI's catalog
+  schema requires `supported_endpoints` on every model.
+- `.github/workflows/inference--fast-cli-e2e.yml` — live end-to-end against
+  **prod** (`api.inference.net`): installs the real harness binaries, connects
+  them, and runs a two-turn probe per model — the second turn must reply and
+  show a prompt-cache read covering most of the request (the "only the new
+  message is uncached" invariant). Runs nightly against the latest
+  `@inference/fast@beta` on npm. Prod because this is the release gate for the
+  stack users actually hit, and many models are not hosted in dev. Its resolve
+  step also carries the live-catalog contract (the CLI's default models must
+  be present) so a serving-side catalog change fails the nightly run, not an
+  unrelated PR.
+
+To test any integration against any model(s) on demand:
+
+```bash
+gh workflow run inference--fast-cli-e2e.yml \
+  -f harnesses=claude,codex \
+  -f models=glm-5.2-fast,kimi-k3-fast \
+  -f cli_source=npm-beta \
+  -f enable_images=true
+```
+
+`harnesses=all` and `models=default` (the defaults) run every harness against
+its default models. A model that is not in the prod catalog fails the setup
+job before any install starts. The gateway converts every wire API
+(`/v1/messages`, `/v1/responses`, `/v1/chat/completions`) for every hosted
+model, so any catalog model can pair with any harness.
+
+To run the same probe locally against prod with your own harness installs
+(seed a config.json with a machine key first, e.g. by running `fast login`
+against prod once and copying `~/.inference-fast/config.json`):
+
+```bash
+INFERENCE_FAST_CONFIG_DIR=<state-dir-with-config.json> \
+INFERENCE_FAST_RELAY_URL=https://relay.inference.net \
+INFERENCE_FAST_API_URL=https://api.inference.net \
+HARNESS=claude MODEL=claude-haiku-4-5 \
+bun run test:live
+# add ENABLE_IMAGES=true MODEL_VISION=true to include the image probe
+```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@inference/fast",
-  "version": "0.0.38",
+  "version": "0.0.40-beta.89",
   "description": "Connect coding agents to fast Inference.net models",
   "type": "module",
   "license": "MIT",
@@ -24,10 +24,10 @@
     "pi"
   ],
   "optionalDependencies": {
-    "@inference/fast-darwin-arm64": "0.0.38",
-    "@inference/fast-darwin-x64": "0.0.38",
-    "@inference/fast-linux-x64": "0.0.38",
-    "@inference/fast-linux-arm64": "0.0.38"
+    "@inference/fast-darwin-arm64": "0.0.40-beta.89",
+    "@inference/fast-darwin-x64": "0.0.40-beta.89",
+    "@inference/fast-linux-x64": "0.0.40-beta.89",
+    "@inference/fast-linux-arm64": "0.0.40-beta.89"
   },
   "scripts": {
     "build": "bun run clean:bin && bun run build:cli",
@@ -49,6 +49,9 @@
     "lint:fix": "cd ../.. && ./node_modules/.bin/oxlint --type-aware --fix --config oxlint.config.mjs apps/fast-cli",
     "tsc": "../../node_modules/typescript-7/bin/tsc --build",
     "test": "vitest run --config vitest.config.ts",
-    "test:unit": "vitest run --config vitest.config.ts"
+    "test:e2e": "vitest run --config vitest.e2e.config.ts",
+    "test:integration": "vitest run --config vitest.config.ts tests/integration",
+    "test:live": "vitest run --config vitest.live.config.ts",
+    "test:unit": "vitest run --config vitest.config.ts tests/unit"
   }
 }