@bilalimamoglu/sift 0.4.2 → 0.4.4

package/README.md

@@ -1,22 +1,45 @@
+<div align="center">
+
+<img src="assets/brand/sift-logo-minimal-teal-default.svg" alt="sift logo" width="220" />
+
 # sift
 
+### Turn noisy command output into actionable diagnoses for your coding agent
+
+**Benchmark-backed test triage - Heuristic-first reductions - Agent-ready terminal workflows**
+
 [![npm version](https://img.shields.io/npm/v/@bilalimamoglu/sift)](https://www.npmjs.com/package/@bilalimamoglu/sift)
 [![license](https://img.shields.io/github/license/bilalimamoglu/sift)](LICENSE)
 [![CI](https://img.shields.io/github/actions/workflow/status/bilalimamoglu/sift/ci.yml?branch=main&label=CI)](https://github.com/bilalimamoglu/sift/actions/workflows/ci.yml)
+[![Node.js](https://img.shields.io/badge/Node.js-20+-green.svg)](https://nodejs.org/)
 
-Turn 13,000 lines of test output into 2 root causes.
+<br />
+
+### Get Started
+
+```bash
+npm install -g @bilalimamoglu/sift
+```
+
+<sub>Works with pytest, vitest, jest, tsc, ESLint, webpack, Cargo, terraform, npm audit, and more.</sub>
+
+</div>
+
+---
 
-Your agent reads a diagnosis, not a log file.
+## Why Sift?
+
+When an agent hits noisy output, it burns budget reading logs instead of fixing the problem.
+
+`sift` sits in front of that output and reduces it into a small, actionable first pass. Your agent reads the diagnosis, not the wall of text.
+
+Turn 13,000 lines of test output into 2 root causes.
 
 <p align="center">
   <img src="assets/readme/test-status-demo.gif" alt="sift turning a pytest failure wall into a short diagnosis" width="960" />
 </p>
 
-## Before / After
-
-128 test failures. 13,000 lines of logs. The agent reads all of it.
-
-With `sift`, it reads this instead:
+With `sift`, the same run becomes:
 
 ```text
 - Tests did not pass.
@@ -30,20 +53,118 @@ With `sift`, it reads this instead:
 - Decision: stop and act.
 ```
 
-Same diagnosis. One run compressed from 198,000 tokens to 129.
+In the largest benchmark fixture, sift compressed 198,026 raw output tokens to 129. That is what the agent reads instead of the full log.
+
+---
+
+## Benchmark Results
+
+The output reduction above measures a single command's raw output. The table below measures the full end-to-end debug session: how many tokens, tool calls, and seconds the agent spends to reach the same diagnosis.
+
+Real debug loop on a 640-test Python backend with 124 repeated setup errors, 3 contract failures, and 511 passing tests:
+
+| Metric | Without sift | With sift | Reduction |
+|--------|-------------:|----------:|----------:|
+| Tokens | 52,944 | 20,049 | 62% fewer |
+| Tool calls | 40.8 | 12 | 71% fewer |
+| Wall-clock time | 244s | 85s | 65% faster |
+| Commands | 15.5 | 6 | 61% fewer |
+| Diagnosis | Same | Same | Same outcome |
+
+Same diagnosis, less agent thrash.
+
+Methodology and caveats: [BENCHMARK_NOTES.md](BENCHMARK_NOTES.md)
+
+---
+
+## How It Works
+
+`sift` keeps the explanation simple:
+
+1. **Capture output.** Run the noisy command or accept already-existing piped output.
+2. **Run local heuristics.** Detect known failure shapes first so common cases stay cheap and deterministic.
+3. **Return the diagnosis.** When heuristics are confident, `sift` gives the agent the root cause, anchor, and next step.
+4. **Fall back only when needed.** If heuristics are not enough, `sift` uses a cheaper model instead of spending your main agent budget.
+
+Your agent spends tokens fixing, not reading.
+
+---
+
+## Key Features
+
+<table>
+<tr>
+<td width="33%" valign="top">
+
+### Test Failure Triage
+Collapse repeated pytest, vitest, and jest failures into a short diagnosis with root-cause buckets, anchors, and fix hints.
+
+</td>
+<td width="33%" valign="top">
+
+### Typecheck and Lint Reduction
+Group noisy `tsc` and ESLint output into the few issues that actually matter instead of dumping the whole log back into the model.
+
+</td>
+<td width="33%" valign="top">
+
+### Build Failure Extraction
+Pull out the first concrete error from webpack, esbuild/Vite, Cargo, Go, GCC/Clang, and similar build output.
+
+</td>
+</tr>
+<tr>
+<td width="33%" valign="top">
+
+### Audit and Infra Risk
+Surface high-impact `npm audit` findings and destructive `terraform plan` signals without making the agent read everything.
+
+</td>
+<td width="33%" valign="top">
+
+### Heuristic-First by Default
+Every built-in preset tries local parsing first. When the heuristic handles the output, no provider call is needed.
+
+</td>
+<td width="33%" valign="top">
+
+### Agent and Automation Friendly
+Use `sift` in Codex, Claude, CI, hooks, or shell scripts so downstream tooling gets short, structured answers instead of raw noise.
+
+</td>
+</tr>
+</table>
+
+---
+
+## Setup and Agent Integration
+
+Most built-in presets run entirely on local heuristics with no API key needed. For presets that fall back to a model (`diff-summary`, `log-errors`, or when heuristics are not confident enough), sift supports OpenAI-compatible and OpenRouter-compatible endpoints.
+
+Set up the provider first, then install the managed instruction block for the agent you want to steer:
+
+```bash
+sift config setup
+sift doctor
+sift agent install codex
+sift agent install claude
+```
+
+You can also preview, inspect, or remove those blocks:
+
+```bash
+sift agent show codex
+sift agent status
+sift agent remove codex
+```
 
-## Not just tests
+Command-first details live in [docs/cli-reference.md](docs/cli-reference.md).
 
-The same idea applies across noisy dev workflows:
+---
 
-- **Type errors** → grouped by error code, no model call
-- **Lint output** → grouped by rule, no model call
-- **Build failures** → first real error from webpack, esbuild/Vite, Cargo, Go, GCC/Clang
-- **`npm audit`** → high/critical vulnerabilities only, no model call
-- **`terraform plan`** → destructive risk detection, no model call
-- **Diffs and logs** → compressed through a cheaper model before reaching your agent
+## Quick Start
 
-## Install
+### 1. Install
 
 ```bash
 npm install -g @bilalimamoglu/sift
@@ -51,109 +172,115 @@ npm install -g @bilalimamoglu/sift
 
 Requires Node.js 20+.
 
-## Try it
+### 2. Run Sift in front of a noisy command
 
 ```bash
 sift exec --preset test-status -- pytest -q
-sift exec --preset test-status -- npx vitest run
-sift exec --preset test-status -- npx jest
 ```
 
-Other workflows:
+Other common entry points:
 
 ```bash
-sift exec --preset typecheck-summary -- npx tsc --noEmit
-sift exec --preset lint-failures -- npx eslint src/
-sift exec --preset build-failure -- npm run build
-sift exec --preset audit-critical -- npm audit
-sift exec --preset infra-risk -- terraform plan
+sift exec --preset test-status -- npx vitest run
+sift exec --preset test-status -- npx jest
 sift exec "what changed?" -- git diff
 ```
 
-## How it works
-
-`sift` sits between a noisy command and a coding agent.
+### 3. Zoom only if needed
 
-1. Capture output.
-2. Run local heuristics for known failure shapes.
-3. If heuristics are confident, return the diagnosis. No model call.
-4. If not, call a cheaper model — not your agent's.
+Think of the workflow like this:
 
-The agent gets the root cause, where it happens, and what to do next.
+- `standard` = map
+- `focused` = zoom
+- raw traceback = last resort
 
-So your agent spends tokens fixing, not reading.
+```bash
+sift rerun
+sift rerun --remaining --detail focused
+```
 
-## Built-in presets
+If `standard` already gives you the root cause, anchor, and fix, stop there and act.
 
-Every preset runs local heuristics first. When the heuristic handles the output, the provider is never called.
+---
 
-| Preset | What it does |
-|--------|-------------|
-| `test-status` | Groups pytest, vitest, jest failures into root-cause buckets with anchors and fix suggestions. 30+ failure patterns. |
-| `typecheck-summary` | Parses `tsc` output, groups by error code, returns max 5 bullets. No model call. |
-| `lint-failures` | Parses ESLint output, groups by rule, detects fixable hints. No model call. |
-| `build-failure` | Extracts first concrete error from webpack, esbuild/Vite, Cargo, Go, GCC/Clang, `tsc --build`. Falls back to model for unsupported formats. |
-| `audit-critical` | Extracts high/critical vulnerabilities from `npm audit`. No model call. |
-| `infra-risk` | Detects destructive signals in `terraform plan`. No model call. |
-| `diff-summary` | Summarizes changes and risks in diff output. |
-| `log-errors` | Extracts top error signals from log output. |
+## Presets
 
-## Benchmark
+| Preset | What it does | Needs provider? |
+|--------|--------------|:---------------:|
+| `test-status` | Groups pytest, vitest, and jest failures into root-cause buckets with anchors and fix suggestions. | No |
+| `typecheck-summary` | Parses `tsc` output and groups issues by error code. | No |
+| `lint-failures` | Parses ESLint output and groups failures by rule. | No |
+| `build-failure` | Extracts the first concrete build error from common toolchains. | Fallback only |
+| `audit-critical` | Pulls high and critical `npm audit` findings. | No |
+| `infra-risk` | Detects destructive signals in `terraform plan`. | No |
+| `diff-summary` | Summarizes change sets and likely risks in diff output. | Yes |
+| `log-errors` | Extracts the strongest error signals from noisy logs. | Fallback only |
 
-End-to-end debug loop on a real 640-test Python backend (125 repeated setup errors, 3 contract failures, 510 passing tests):
+When output already exists in a pipeline, use pipe mode instead of `exec`:
 
-| Metric | Without sift | With sift | Reduction |
-|--------|-------------|-----------|-----------|
-| Tokens | 52,944 | 20,049 | 62% fewer |
-| Tool calls | 40.8 | 12 | 71% fewer |
-| Wall-clock time | 244s | 85s | 65% faster |
-| Commands | 15.5 | 6 | 61% fewer |
-| Diagnosis | Same | Same | — |
+```bash
+pytest -q 2>&1 | sift preset test-status
+npm audit 2>&1 | sift preset audit-critical
+```
 
-Methodology and caveats: [BENCHMARK_NOTES.md](BENCHMARK_NOTES.md)
+---
 
-## Test debugging workflow
+## Test Debugging Workflow
 
-Think of it like this:
-- `standard` = map
-- `focused` = zoom
-- raw traceback = last resort
+For noisy test failures, start with the `test-status` preset and let `standard` be the default stop point.
 
 ```bash
 sift exec --preset test-status -- <test command>
 sift rerun
 sift rerun --remaining --detail focused
+sift rerun --remaining --detail verbose --show-raw
 ```
 
-If `standard` already gives you the root cause, anchor, and fix — stop and act.
-
-`sift rerun --remaining` narrows automatically for cached `pytest` runs. For `vitest` and `jest`, it reruns the full command and keeps diagnosis focused on what still fails.
+Useful rules of thumb:
 
-## Setup
+- If `standard` ends with `Decision: stop and act`, go read source and fix the issue.
+- Use `sift rerun` after a change to refresh the same test command at `standard`.
+- Use `sift rerun --remaining` to zoom into what still fails after the first pass.
+- Treat raw traceback as the last resort, not the starting point.
 
-Guided setup writes a config, verifies the provider, and makes daily use easier:
+For machine branching or automation, `test-status` also supports diagnose JSON:
 
 ```bash
-sift config setup
-sift doctor
+sift exec --preset test-status --goal diagnose --format json -- pytest -q
+sift rerun --goal diagnose --format json
 ```
 
-To wire `sift` into your coding agent automatically:
+---
 
-```bash
-sift agent install claude
-sift agent install codex
-```
+## Limitations
+
+- sift adds the most value when output is long, repetitive, and shaped by a small number of root causes. For short, obvious failures it may not save much.
+- The deepest local heuristic coverage is in test debugging (pytest, vitest, jest). Other presets have solid heuristics but less depth.
+- sift does not help with interactive or TUI-based commands.
+- When heuristics cannot explain the output confidently, sift falls back to a provider. If no provider is configured, it returns what the heuristics could extract and signals that raw output may still be needed.
 
-Config details: [docs/cli-reference.md](docs/cli-reference.md)
+---
 
 ## Docs
 
 - CLI reference: [docs/cli-reference.md](docs/cli-reference.md)
 - Worked examples: [docs/examples](docs/examples)
 - Benchmark methodology: [BENCHMARK_NOTES.md](BENCHMARK_NOTES.md)
+- Contributing and development notes: [CONTRIBUTING.md](CONTRIBUTING.md)
 - Release notes: [release-notes](release-notes)
 
+---
+
 ## License
 
 MIT
+
+---
+
+<div align="center">
+
+Built for agent-first terminal workflows.
+
+[Report Bug](https://github.com/bilalimamoglu/sift/issues) | [Request Feature](https://github.com/bilalimamoglu/sift/issues)
+
+</div>

package/dist/cli.js

@@ -5,13 +5,15 @@ import { createRequire } from "module";
 import { cac } from "cac";
 
 // src/config/load.ts
-import fs from "fs";
+import fs2 from "fs";
 import path2 from "path";
 import YAML from "yaml";
 
 // src/constants.ts
+import fs from "fs";
 import os from "os";
 import path from "path";
+import crypto from "crypto";
 var DEFAULT_CONFIG_FILENAME = "sift.config.yaml";
 function getDefaultCodexGlobalInstructionsPath(homeDir = os.homedir()) {
   return path.join(homeDir, ".codex", "AGENTS.md");
@@ -28,6 +30,26 @@ function getDefaultGlobalStateDir(homeDir = os.homedir()) {
 function getDefaultTestStatusStatePath(homeDir = os.homedir()) {
   return path.join(getDefaultGlobalStateDir(homeDir), "last-test-status.json");
 }
+function getDefaultScopedTestStatusStateDir(homeDir = os.homedir()) {
+  return path.join(getDefaultGlobalStateDir(homeDir), "test-status", "by-cwd");
+}
+function getScopedTestStatusStatePath(cwd, homeDir = os.homedir()) {
+  const normalizedCwd = normalizeScopedCacheCwd(cwd);
+  const baseName = slugCachePathSegment(path.basename(normalizedCwd)) || "root";
+  const shortHash = crypto.createHash("sha256").update(normalizedCwd).digest("hex").slice(0, 10);
+  return path.join(getDefaultScopedTestStatusStateDir(homeDir), `${baseName}-${shortHash}.json`);
+}
+function slugCachePathSegment(value) {
+  return value.trim().toLowerCase().replace(/[^a-z0-9._-]+/g, "-").replace(/^-+|-+$/g, "");
+}
+function normalizeScopedCacheCwd(cwd) {
+  const absoluteCwd = path.resolve(cwd);
+  try {
+    return fs.realpathSync.native(absoluteCwd);
+  } catch {
+    return absoluteCwd;
+  }
+}
 function getDefaultConfigSearchPaths() {
   return [
     path.resolve(process.cwd(), "sift.config.yaml"),
@@ -44,13 +66,13 @@ var CAPTURE_OMITTED_MARKER = "\n...[captured output omitted]...\n";
 function findConfigPath(explicitPath) {
   if (explicitPath) {
     const resolved = path2.resolve(explicitPath);
-    if (!fs.existsSync(resolved)) {
+    if (!fs2.existsSync(resolved)) {
       throw new Error(`Config file not found: ${resolved}`);
     }
     return resolved;
   }
   for (const candidate of getDefaultConfigSearchPaths()) {
-    if (fs.existsSync(candidate)) {
+    if (fs2.existsSync(candidate)) {
       return candidate;
     }
   }
@@ -61,7 +83,7 @@ function loadRawConfig(explicitPath) {
   if (!configPath) {
     return {};
   }
-  const content = fs.readFileSync(configPath, "utf8");
+  const content = fs2.readFileSync(configPath, "utf8");
   return YAML.parse(content) ?? {};
 }
 
@@ -472,7 +494,7 @@ function resolveConfig(options = {}) {
 }
 
 // src/config/write.ts
-import fs2 from "fs";
+import fs3 from "fs";
 import path3 from "path";
 import YAML2 from "yaml";
 function writeExampleConfig(options = {}) {
@@ -480,34 +502,41 @@ function writeExampleConfig(options = {}) {
     throw new Error("Use either --path <path> or --global, not both.");
   }
   const resolved = options.global ? getDefaultGlobalConfigPath() : path3.resolve(options.targetPath ?? DEFAULT_CONFIG_FILENAME);
-  if (fs2.existsSync(resolved)) {
+  if (fs3.existsSync(resolved)) {
     throw new Error(`Config file already exists at ${resolved}`);
   }
   const yaml = YAML2.stringify(defaultConfig);
-  fs2.mkdirSync(path3.dirname(resolved), { recursive: true });
-  fs2.writeFileSync(resolved, yaml, "utf8");
+  fs3.mkdirSync(path3.dirname(resolved), { recursive: true });
+  fs3.writeFileSync(resolved, yaml, {
+    encoding: "utf8",
+    mode: 384
+  });
+  try {
+    fs3.chmodSync(resolved, 384);
+  } catch {
+  }
   return resolved;
 }
 function writeConfigFile(options) {
   const resolved = path3.resolve(options.targetPath);
-  if (!options.overwrite && fs2.existsSync(resolved)) {
+  if (!options.overwrite && fs3.existsSync(resolved)) {
     throw new Error(`Config file already exists at ${resolved}`);
   }
   const yaml = YAML2.stringify(options.config);
-  fs2.mkdirSync(path3.dirname(resolved), { recursive: true });
-  fs2.writeFileSync(resolved, yaml, {
+  fs3.mkdirSync(path3.dirname(resolved), { recursive: true });
+  fs3.writeFileSync(resolved, yaml, {
     encoding: "utf8",
     mode: 384
   });
   try {
-    fs2.chmodSync(resolved, 384);
+    fs3.chmodSync(resolved, 384);
   } catch {
   }
   return resolved;
 }
 
 // src/config/editable.ts
-import fs3 from "fs";
+import fs4 from "fs";
 import path4 from "path";
 function isRecord2(value) {
   return Boolean(value) && typeof value === "object" && !Array.isArray(value);
@@ -520,7 +549,7 @@ function resolveEditableConfigPath(explicitPath) {
 }
 function loadEditableConfig(explicitPath) {
   const resolvedPath = resolveEditableConfigPath(explicitPath);
-  const existed = fs3.existsSync(resolvedPath);
+  const existed = fs4.existsSync(resolvedPath);
   const rawConfig = existed ? loadRawConfig(resolvedPath) : {};
   const config = siftConfigSchema.parse(
     mergeDefined(defaultConfig, isRecord2(rawConfig) ? rawConfig : {})
@@ -1157,7 +1186,7 @@ function configUse(provider, configPath, env = process.env) {
 }
 
 // src/commands/agent.ts
-import fs4 from "fs";
+import fs5 from "fs";
 import os2 from "os";
 import path6 from "path";
 import { createInterface as createInterface2 } from "readline/promises";
@@ -1787,28 +1816,49 @@ function joinAroundRemoval(before, after, eol) {
   return `${left}${eol}${eol}${right}`;
 }
 function readOptionalFile(targetPath) {
-  if (!fs4.existsSync(targetPath)) {
+  if (!fs5.existsSync(targetPath)) {
     return void 0;
   }
-  const stats = fs4.statSync(targetPath);
+  const stats = fs5.statSync(targetPath);
   if (!stats.isFile()) {
     throw new Error(`${targetPath} exists but is not a file.`);
   }
-  return fs4.readFileSync(targetPath, "utf8");
+  return fs5.readFileSync(targetPath, "utf8");
 }
 function writeTextFileAtomic(targetPath, content) {
-  fs4.mkdirSync(path6.dirname(targetPath), { recursive: true });
+  fs5.mkdirSync(path6.dirname(targetPath), { recursive: true });
   const tempPath = `${targetPath}.tmp-${process.pid}-${Date.now()}`;
-  fs4.writeFileSync(tempPath, content, "utf8");
-  fs4.renameSync(tempPath, targetPath);
+  fs5.writeFileSync(tempPath, content, "utf8");
+  fs5.renameSync(tempPath, targetPath);
 }
 function escapeRegExp(value) {
   return value.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
 }
 
 // src/commands/doctor.ts
+var PLACEHOLDER_API_KEYS = [
+  "YOUR_API_KEY",
+  "your_api_key",
+  "your-api-key",
+  "sk-xxx",
+  "sk-placeholder",
+  "CHANGE_ME",
+  "change_me",
+  "TODO",
+  "todo",
+  "xxx",
+  "XXX"
+];
+function isPlaceholderApiKey(key) {
+  if (!key) return false;
+  return PLACEHOLDER_API_KEYS.includes(key.trim());
+}
+function isRealApiKey(key) {
+  return Boolean(key) && !isPlaceholderApiKey(key);
+}
 function runDoctor(config, configPath) {
   const ui = createPresentation(Boolean(process.stdout.isTTY));
+  const apiKeyStatus = isRealApiKey(config.provider.apiKey) ? "set" : isPlaceholderApiKey(config.provider.apiKey) ? "placeholder (not a real key)" : "not set";
   const lines = [
     "sift doctor",
     "A quick check for your local setup.",
@@ -1817,7 +1867,7 @@ function runDoctor(config, configPath) {
     ui.labelValue("provider", config.provider.provider),
     ui.labelValue("model", config.provider.model),
     ui.labelValue("baseUrl", config.provider.baseUrl),
-    ui.labelValue("apiKey", config.provider.apiKey ? "set" : "not set"),
+    ui.labelValue("apiKey", apiKeyStatus),
     ui.labelValue("maxCaptureChars", String(config.input.maxCaptureChars)),
     ui.labelValue("maxInputChars", String(config.input.maxInputChars)),
     ui.labelValue("rawFallback", String(config.runtime.rawFallback))
@@ -1831,8 +1881,12 @@ function runDoctor(config, configPath) {
   if (!config.provider.model) {
     problems.push("Missing provider.model");
   }
-  if ((config.provider.provider === "openai" || config.provider.provider === "openai-compatible" || config.provider.provider === "openrouter") && !config.provider.apiKey) {
-    problems.push("Missing provider.apiKey");
+  if ((config.provider.provider === "openai" || config.provider.provider === "openai-compatible" || config.provider.provider === "openrouter") && !isRealApiKey(config.provider.apiKey)) {
+    if (isPlaceholderApiKey(config.provider.apiKey)) {
+      problems.push(`provider.apiKey looks like a placeholder: "${config.provider.apiKey}"`);
+    } else {
+      problems.push("Missing provider.apiKey");
+    }
     problems.push(
       `Set one of: ${getProviderApiKeyEnvNames(
         config.provider.provider,
@@ -1951,6 +2005,7 @@ var OpenAIProvider = class {
         signal: controller.signal,
         headers: {
           "content-type": "application/json",
+          connection: "close",
           ...this.apiKey ? { authorization: `Bearer ${this.apiKey}` } : {}
         },
         body: JSON.stringify({
@@ -2051,6 +2106,7 @@ var OpenAICompatibleProvider = class {
         signal: controller.signal,
         headers: {
           "content-type": "application/json",
+          connection: "close",
           ...this.apiKey ? { authorization: `Bearer ${this.apiKey}` } : {}
         },
         body: JSON.stringify({
@@ -8233,7 +8289,7 @@ function emitStatsFooter(args) {
 }
 
 // src/core/testStatusState.ts
-import fs5 from "fs";
+import fs6 from "fs";
 import path7 from "path";
 import { z as z3 } from "zod";
 var detailSchema = z3.enum(["standard", "focused", "verbose"]);
@@ -8683,7 +8739,7 @@ function migrateCachedTestStatusRun(state) {
 function readCachedTestStatusRun(statePath = getDefaultTestStatusStatePath()) {
   let raw = "";
   try {
-    raw = fs5.readFileSync(statePath, "utf8");
+    raw = fs6.readFileSync(statePath, "utf8");
   } catch (error) {
     if (error.code === "ENOENT") {
       throw new MissingCachedTestStatusRunError();
@@ -8704,10 +8760,10 @@ function tryReadCachedTestStatusRun(statePath = getDefaultTestStatusStatePath())
   }
 }
 function writeCachedTestStatusRun(state, statePath = getDefaultTestStatusStatePath()) {
-  fs5.mkdirSync(path7.dirname(statePath), {
+  fs6.mkdirSync(path7.dirname(statePath), {
     recursive: true
   });
-  fs5.writeFileSync(statePath, `${JSON.stringify(state, null, 2)}
+  fs6.writeFileSync(statePath, `${JSON.stringify(state, null, 2)}
 `, "utf8");
 }
 function getNextEscalationDetail(detail) {
@@ -8869,7 +8925,8 @@ function resolveEscalationDetail(state, requested, showRaw = false) {
   return nextDetail;
 }
 async function runEscalate(request) {
-  const state = readCachedTestStatusRun();
+  const scopedStatePath = getScopedTestStatusStatePath(process.cwd());
+  const state = readCachedTestStatusRun(scopedStatePath);
   const detail = resolveEscalationDetail(state, request.detail, request.showRaw);
   if (request.verbose) {
     process.stderr.write(
@@ -8917,10 +8974,13 @@ async function runEscalate(request) {
     quiet: Boolean(request.quiet)
   });
   try {
-    writeCachedTestStatusRun({
-      ...state,
-      detail
-    });
+    writeCachedTestStatusRun(
+      {
+        ...state,
+        detail
+      },
+      scopedStatePath
+    );
   } catch (error) {
     if (request.verbose) {
       const reason = error instanceof Error ? error.message : "unknown_error";
@@ -9261,10 +9321,11 @@ async function runExec(request) {
   const shellPath = process.env.SHELL || "/bin/bash";
   const commandPreview = buildCommandPreview(request);
   const commandCwd = request.cwd ?? process.cwd();
+  const scopedStatePath = getScopedTestStatusStatePath(commandCwd);
   const isTestStatusPreset = request.presetName === "test-status";
   const readCachedBaseline = isTestStatusPreset && (request.readCachedBaseline ?? true);
   const writeCachedBaselineRequested = isTestStatusPreset && (request.writeCachedBaseline ?? (request.skipCacheWrite ? false : true));
-  const previousCachedRun = readCachedBaseline ? tryReadCachedTestStatusRun() : null;
+  const previousCachedRun = readCachedBaseline ? tryReadCachedTestStatusRun(scopedStatePath) : null;
   if (request.config.runtime.verbose) {
     process.stderr.write(
       `${pc5.dim("sift")} exec mode=${hasShellCommand ? "shell" : "argv"} command=${commandPreview}
@@ -9467,7 +9528,7 @@ ${output}`;
       }
       if (currentCachedRun && shouldWriteCachedBaseline) {
         try {
-          writeCachedTestStatusRun(currentCachedRun);
+          writeCachedTestStatusRun(currentCachedRun, scopedStatePath);
         } catch (error) {
           if (request.config.runtime.verbose) {
             const reason = error instanceof Error ? error.message : "unknown_error";
@@ -9503,7 +9564,7 @@ ${output}`;
 
 // src/core/rerun.ts
 async function runRerun(request) {
-  const state = readCachedTestStatusRun();
+  const state = readCachedTestStatusRun(getScopedTestStatusStatePath(process.cwd()));
   if (!request.remaining) {
     return runExec({
       ...request,

package/dist/index.js

@@ -4,8 +4,10 @@ import { constants as osConstants } from "os";
 import pc3 from "picocolors";
 
 // src/constants.ts
+import fs from "fs";
 import os from "os";
 import path from "path";
+import crypto from "crypto";
 function getDefaultGlobalConfigPath(homeDir = os.homedir()) {
   return path.join(homeDir, ".config", "sift", "config.yaml");
 }
@@ -15,6 +17,26 @@ function getDefaultGlobalStateDir(homeDir = os.homedir()) {
 function getDefaultTestStatusStatePath(homeDir = os.homedir()) {
   return path.join(getDefaultGlobalStateDir(homeDir), "last-test-status.json");
 }
+function getDefaultScopedTestStatusStateDir(homeDir = os.homedir()) {
+  return path.join(getDefaultGlobalStateDir(homeDir), "test-status", "by-cwd");
+}
+function getScopedTestStatusStatePath(cwd, homeDir = os.homedir()) {
+  const normalizedCwd = normalizeScopedCacheCwd(cwd);
+  const baseName = slugCachePathSegment(path.basename(normalizedCwd)) || "root";
+  const shortHash = crypto.createHash("sha256").update(normalizedCwd).digest("hex").slice(0, 10);
+  return path.join(getDefaultScopedTestStatusStateDir(homeDir), `${baseName}-${shortHash}.json`);
+}
+function slugCachePathSegment(value) {
+  return value.trim().toLowerCase().replace(/[^a-z0-9._-]+/g, "-").replace(/^-+|-+$/g, "");
+}
+function normalizeScopedCacheCwd(cwd) {
+  const absoluteCwd = path.resolve(cwd);
+  try {
+    return fs.realpathSync.native(absoluteCwd);
+  } catch {
+    return absoluteCwd;
+  }
+}
 function getDefaultConfigSearchPaths() {
   return [
     path.resolve(process.cwd(), "sift.config.yaml"),
@@ -4741,6 +4763,7 @@ var OpenAIProvider = class {
         signal: controller.signal,
         headers: {
           "content-type": "application/json",
+          connection: "close",
           ...this.apiKey ? { authorization: `Bearer ${this.apiKey}` } : {}
         },
         body: JSON.stringify({
@@ -4841,6 +4864,7 @@ var OpenAICompatibleProvider = class {
         signal: controller.signal,
         headers: {
           "content-type": "application/json",
+          connection: "close",
           ...this.apiKey ? { authorization: `Bearer ${this.apiKey}` } : {}
         },
         body: JSON.stringify({
@@ -6413,7 +6437,7 @@ function emitStatsFooter(args) {
 }
 
 // src/core/testStatusState.ts
-import fs from "fs";
+import fs2 from "fs";
 import path2 from "path";
 import { z as z2 } from "zod";
 var detailSchema = z2.enum(["standard", "focused", "verbose"]);
@@ -6863,7 +6887,7 @@ function migrateCachedTestStatusRun(state) {
 function readCachedTestStatusRun(statePath = getDefaultTestStatusStatePath()) {
   let raw = "";
   try {
-    raw = fs.readFileSync(statePath, "utf8");
+    raw = fs2.readFileSync(statePath, "utf8");
   } catch (error) {
     if (error.code === "ENOENT") {
       throw new MissingCachedTestStatusRunError();
@@ -6884,10 +6908,10 @@ function tryReadCachedTestStatusRun(statePath = getDefaultTestStatusStatePath())
   }
 }
 function writeCachedTestStatusRun(state, statePath = getDefaultTestStatusStatePath()) {
-  fs.mkdirSync(path2.dirname(statePath), {
+  fs2.mkdirSync(path2.dirname(statePath), {
     recursive: true
   });
-  fs.writeFileSync(statePath, `${JSON.stringify(state, null, 2)}
+  fs2.writeFileSync(statePath, `${JSON.stringify(state, null, 2)}
 `, "utf8");
 }
 function buildTargetDelta(args) {
@@ -7273,10 +7297,11 @@ async function runExec(request) {
   const shellPath = process.env.SHELL || "/bin/bash";
   const commandPreview = buildCommandPreview(request);
   const commandCwd = request.cwd ?? process.cwd();
+  const scopedStatePath = getScopedTestStatusStatePath(commandCwd);
   const isTestStatusPreset = request.presetName === "test-status";
   const readCachedBaseline = isTestStatusPreset && (request.readCachedBaseline ?? true);
   const writeCachedBaselineRequested = isTestStatusPreset && (request.writeCachedBaseline ?? (request.skipCacheWrite ? false : true));
-  const previousCachedRun = readCachedBaseline ? tryReadCachedTestStatusRun() : null;
+  const previousCachedRun = readCachedBaseline ? tryReadCachedTestStatusRun(scopedStatePath) : null;
   if (request.config.runtime.verbose) {
     process.stderr.write(
       `${pc3.dim("sift")} exec mode=${hasShellCommand ? "shell" : "argv"} command=${commandPreview}
@@ -7479,7 +7504,7 @@ ${output}`;
       }
       if (currentCachedRun && shouldWriteCachedBaseline) {
         try {
-          writeCachedTestStatusRun(currentCachedRun);
+          writeCachedTestStatusRun(currentCachedRun, scopedStatePath);
         } catch (error) {
           if (request.config.runtime.verbose) {
             const reason = error instanceof Error ? error.message : "unknown_error";
@@ -7585,19 +7610,19 @@ var defaultConfig = {
 };
 
 // src/config/load.ts
-import fs2 from "fs";
+import fs3 from "fs";
 import path3 from "path";
 import YAML from "yaml";
 function findConfigPath(explicitPath) {
   if (explicitPath) {
     const resolved = path3.resolve(explicitPath);
-    if (!fs2.existsSync(resolved)) {
+    if (!fs3.existsSync(resolved)) {
       throw new Error(`Config file not found: ${resolved}`);
     }
     return resolved;
   }
   for (const candidate of getDefaultConfigSearchPaths()) {
-    if (fs2.existsSync(candidate)) {
+    if (fs3.existsSync(candidate)) {
       return candidate;
     }
   }
@@ -7608,7 +7633,7 @@ function loadRawConfig(explicitPath) {
   if (!configPath) {
     return {};
   }
-  const content = fs2.readFileSync(configPath, "utf8");
+  const content = fs3.readFileSync(configPath, "utf8");
   return YAML.parse(content) ?? {};
 }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bilalimamoglu/sift",
-  "version": "0.4.2",
+  "version": "0.4.4",
   "description": "Agent-first command-output reduction layer for agents, CI, and automation.",
   "type": "module",
   "bin": {
@@ -25,8 +25,10 @@
     "bench:report": "node --import tsx scripts/bench/generate-progress-report.ts",
     "dev": "tsx src/cli.ts",
     "typecheck": "tsc --noEmit",
-    "test": "vitest run",
-    "test:coverage": "vitest run --coverage",
+    "test": "vitest run --config vitest.config.ts",
+    "test:smoke": "vitest run --config vitest.config.ts test/*.smoke.test.ts",
+    "test:e2e": "vitest run --config vitest.e2e.config.ts test/*.e2e.test.ts",
+    "test:coverage": "vitest run --config vitest.config.ts --coverage --exclude=\"test/**/*.smoke.test.ts\" --exclude=\"test/**/*.e2e.test.ts\"",
     "test:watch": "vitest",
     "prepublishOnly": "npm run typecheck && npm run test:coverage && npm run build"
   },