@apmantza/greedysearch-pi 1.5.0 → 1.6.0

package/CHANGELOG.md

@@ -1,5 +1,24 @@
 # Changelog
 
+## v1.6.0 (2026-03-29)
+
+### Breaking Changes (Backward Compatible)
+- **Merged deep_research into greedy_search** — new `depth` parameter with three levels:
+  - `fast`: single engine (~15-30s)
+  - `standard`: 3 engines + synthesis (~30-90s, default for `engine: "all"`)
+  - `deep`: 3 engines + source fetching + synthesis + confidence (~60-180s)
+- **Simpler mental model** — one tool with clear speed/quality tradeoffs instead of separate tools with overlapping flags
+- **Deprecated flags still work** — `--synthesize` maps to `depth: "standard"`, `--deep-research` maps to `depth: "deep"`
+- **deep_research tool aliased** — still works, calls `greedy_search` with `depth: "deep"`
+
+### Documentation
+- Updated README with new `depth` parameter and examples
+- Updated skill documentation (SKILL.md) to reflect simplified API
+
+## v1.5.1 (2026-03-29)
+
+- **Fixed npm package** — added `.pi-lens/` and test files to `.npmignore` to reduce package size
+
 ## v1.5.0 (2026-03-29)
 
 ### Features

package/README.md

@@ -24,10 +24,10 @@ pi install git:github.com/apmantza/GreedySearch-pi
 
 ## Quick Start
 
-Once installed, Pi gains a `greedy_search` tool. The model will use it automatically for questions about current libraries, error messages, version-specific docs, etc.
+Once installed, Pi gains a `greedy_search` tool with three depth levels.
 
 ```
-greedy_search({ query: "What's new in React 19?", engine: "all" })
+greedy_search({ query: "What's new in React 19?", depth: "standard" })
 ```
 
 ## Parameters
@@ -35,19 +35,27 @@ greedy_search({ query: "What's new in React 19?", engine: "all" })
 | Parameter | Type | Default | Description |
 |-----------|------|---------|-------------|
 | `query` | string | required | The search question |
-| `engine` | string | `"all"` | Engine to use (see below) |
-| `synthesize` | boolean | `false` | Synthesize results into one answer via Gemini |
+| `engine` | string | `"all"` | `all`, `perplexity`, `bing`, `google`, `gemini` |
+| `depth` | string | `"standard"` | `fast` (1 engine), `standard` (3 engines + synthesis), `deep` (3 + fetch + synthesis + confidence) |
 | `fullAnswer` | boolean | `false` | Return complete answer (~3000+ chars) vs truncated preview (~300 chars) |
 
-## Engines
+## Depth Levels
 
-| Engine | Alias | Latency | Best for |
-|--------|-------|---------|----------|
-| `all` | — | 30-90s | Highest confidence — all 3 engines in parallel (default) |
-| `perplexity` | `p` | 15-30s | Technical Q&A, code explanations, documentation |
-| `bing` | `b` | 15-30s | Recent news, Microsoft ecosystem |
-| `google` | `g` | 15-30s | Broad coverage, multiple perspectives |
-| `gemini` | `gem` | 15-30s | Google's AI with different training data |
+| Depth | Engines | Synthesis | Source Fetch | Time | Best For |
+|-------|---------|-----------|--------------|------|----------|
+| `fast` | 1 | — | — | 15-30s | Quick lookup, single perspective |
+| `standard` | 3 | ✅ | — | 30-90s | Default — balanced speed/quality |
+| `deep` | 3 | ✅ | ✅ (top 5) | 60-180s | Research that matters — architecture decisions |
+
+## Engines (for fast mode)
+
+| Engine | Alias | Best for |
+|--------|-------|----------|
+| `all` | — | All 3 engines — but for fast single-engine, pick one below |
+| `perplexity` | `p` | Technical Q&A, code explanations, documentation |
+| `bing` | `b` | Recent news, Microsoft ecosystem |
+| `google` | `g` | Broad coverage, multiple perspectives |
+| `gemini` | `gem` | Google's AI with different training data |
 
 ## Streaming Progress
 
@@ -60,24 +68,21 @@ When using `engine: "all"`, the tool streams progress as each engine completes:
 **Searching...** ✅ perplexity done · ✅ bing done · ✅ google done
 ```
 
-## Synthesis Mode
+## Deep Research Mode
 
-For complex research questions, use `synthesize: true` with `engine: "all"`:
+For research that matters — architecture decisions, library comparisons — use `depth: "deep"`:
 
 ```
-greedy_search({ query: "best auth patterns for SaaS in 2026", engine: "all", synthesize: true })
+greedy_search({ query: "best auth patterns for SaaS in 2026", depth: "deep" })
 ```
 
-This deduplicates sources across engines, builds a normalized source registry, and feeds that context to Gemini for one clean synthesized answer. Adds ~30s but returns agreement summaries, caveats, key claims, and better-labeled top sources.
+Deep mode: 3 engines + source fetching (top 5) + synthesis + confidence scores. ~60-180s but returns grounded synthesis with fetched evidence.
 
-**Use synthesis when:**
-- You need one definitive answer, not multiple perspectives
-- You're researching a topic to write about or make a decision
-- Token efficiency matters (one answer vs three)
+**Standard vs Deep:**
+- `standard` (default): 3 engines + synthesis. Good for most research.
+- `deep`: Same + fetches source content for grounded answers. Use when the answer really matters.
 
-**Skip synthesis when:**
-- You want to see where engines disagree
-- Speed matters
+**Legacy:** `deep_research` tool still works — aliases to `greedy_search` with `depth: "deep"`.
 
 ## Full vs Short Answers
 
@@ -89,28 +94,28 @@ greedy_search({ query: "explain the React compiler", engine: "perplexity", fullA
 
 ## Examples
 
-**Quick technical lookup:**
+**Quick lookup (fast):**
 
 ```
-greedy_search({ query: "How to use async await in Python", engine: "perplexity" })
+greedy_search({ query: "How to use async await in Python", depth: "fast", engine: "perplexity" })
 ```
 
-**Compare tools (see where engines agree/disagree):**
+**Compare tools (standard):**
 
 ```
-greedy_search({ query: "Prisma vs Drizzle in 2026", engine: "all" })
+greedy_search({ query: "Prisma vs Drizzle in 2026", depth: "standard" })
 ```
 
-**Research with synthesis:**
+**Deep research (architecture decision):**
 
 ```
-greedy_search({ query: "Best practices for monorepo structure", engine: "all", synthesize: true })
+greedy_search({ query: "Best practices for monorepo structure", depth: "deep" })
 ```
 
 **Debug an error:**
 
 ```
-greedy_search({ query: "Error: Cannot find module 'react-dom/client' Next.js 15", engine: "all" })
+greedy_search({ query: "Error: Cannot find module 'react-dom/client' Next.js 15", depth: "standard" })
 ```
 
 ## Requirements
@@ -200,6 +205,15 @@ Sources are now extracted by regex-parsing Markdown links (`[title](url)`) from
 
 ## Changelog
 
+### v1.6.0 (2026-03-29)
+- **Merged deep_research into greedy_search** — new `depth` parameter: `fast` (1 engine), `standard` (3 engines + synthesis), `deep` (3 engines + fetch + synthesis + confidence)
+- **Simpler API** — one tool with clear speed/quality tradeoffs instead of separate tools with overlapping flags
+- **Backward compatible** — `deep_research` still works as alias, `--synthesize` and `--deep-research` flags still function
+- **Updated documentation** — README and skill docs now use `depth` parameter throughout
+
+### v1.5.1 (2026-03-29)
+- Fixed npm package — added `.pi-lens/` and test files to `.npmignore`
+
 ### v1.5.0 (2026-03-29)
 
 - **Code extraction fixed** — `coding_task` now uses clipboard interception to preserve markdown code blocks (was losing them via DOM scraping)

package/index.ts

@@ -456,12 +456,13 @@ export default function greedySearchExtension(pi: ExtensionAPI) {
 					default: "all",
 				},
 			),
-			synthesize: Type.Optional(
-				Type.Boolean({
+			depth: Type.Union(
+				[Type.Literal("fast"), Type.Literal("standard"), Type.Literal("deep")],
+				{
 					description:
-						'When true and engine is "all", deduplicates sources across engines and feeds them to Gemini for a single grounded synthesis. Adds ~30s but saves tokens and improves answer quality.',
-					default: false,
-				}),
+						"Search depth: fast (single engine, ~15-30s), standard (3 engines + synthesis, ~30-90s), deep (3 engines + source fetching + synthesis + confidence, ~60-180s). Default: standard.",
+					default: "standard",
+				},
 			),
 			fullAnswer: Type.Optional(
 				Type.Boolean({
@@ -475,12 +476,12 @@ export default function greedySearchExtension(pi: ExtensionAPI) {
 			const {
 				query,
 				engine = "all",
-				synthesize = false,
+				depth = "standard",
 				fullAnswer = false,
 			} = params as {
 				query: string;
 				engine: string;
-				synthesize?: boolean;
+				depth?: "fast" | "standard" | "deep";
 				fullAnswer?: boolean;
 			};
 
@@ -498,7 +499,11 @@ export default function greedySearchExtension(pi: ExtensionAPI) {
 
 			const flags: string[] = [];
 			if (fullAnswer) flags.push("--full");
-			if (synthesize && engine === "all") flags.push("--synthesize");
+			// Map depth to CLI flags
+			if (depth === "deep") flags.push("--deep");
+			else if (depth === "standard" && engine === "all")
+				flags.push("--synthesize");
+			// For "fast" depth with "all" engine, we run 3 engines but no synthesis (just pick first result)
 
 			// Track progress for "all" engine mode
 			const completed = new Set<string>();
@@ -510,7 +515,8 @@ export default function greedySearchExtension(pi: ExtensionAPI) {
 					if (completed.has(e)) parts.push(`✅ ${e} done`);
 					else parts.push(`⏳ ${e}`);
 				}
-				if (synthesize && completed.size >= 3) parts.push("🔄 synthesizing");
+				if (depth !== "fast" && completed.size >= 3)
+					parts.push("🔄 synthesizing");
 
 				onUpdate?.({
 					content: [
@@ -544,17 +550,15 @@ export default function greedySearchExtension(pi: ExtensionAPI) {
 	});
 
 	// ─── deep_research ─────────────────────────────────────────────────────────
+	// DEPRECATED: Use greedy_search with depth: "deep" instead.
+	// Kept for backward compatibility — aliases to greedy_search.
 	pi.registerTool({
 		name: "deep_research",
-		label: "Deep Research",
+		label: "Deep Research (legacy)",
 		description:
-			"Comprehensive multi-engine research with source fetching and synthesis. " +
-			"Runs Perplexity, Bing Copilot, and Google AI in parallel with full answers, " +
-			"deduplicates and ranks sources by consensus, fetches content from top sources, " +
-			"and synthesizes via Gemini. Returns a structured research document with confidence scores. " +
-			"Use for architecture decisions, library comparisons, best practices, or any research where the answer matters.",
-		promptSnippet:
-			"Deep multi-engine research with source deduplication and synthesis",
+			"DEPRECATED — Use greedy_search with depth: 'deep' instead. " +
+			"Comprehensive multi-engine research with source fetching and synthesis.",
+		promptSnippet: "Deep multi-engine research (legacy alias to greedy_search)",
 		parameters: Type.Object({
 			query: Type.String({ description: "The research question" }),
 		}),
@@ -590,11 +594,11 @@ export default function greedySearchExtension(pi: ExtensionAPI) {
 			};
 
 			try {
-				// Run deep research (includes full answers, synthesis, and source fetching)
+				// Delegate to greedy_search with depth: "deep"
 				const data = await runSearch(
 					"all",
 					query,
-					["--deep-research"],
+					["--deep"],
 					signal,
 					onProgress,
 				);

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@apmantza/greedysearch-pi",
-	"version": "1.5.0",
+	"version": "1.6.0",
 	"description": "Pi extension: multi-engine AI search (Perplexity, Bing Copilot, Google AI) via browser automation — NO API KEYS needed. Extracts answers with sources, optional Gemini synthesis. Grounded AI answers from real browser interactions.",
 	"type": "module",
 	"keywords": [

package/search.mjs

@@ -1070,12 +1070,30 @@ async function main() {
 
 	await ensureChrome();
 
-	const full = args.includes("--full") || args.includes("--deep-research");
+	// Parse --depth or fall back to deprecated flags
+	const depthIdx = args.indexOf("--depth");
+	let depth = "fast"; // default for single engine
+	if (depthIdx !== -1 && args[depthIdx + 1]) {
+		depth = args[depthIdx + 1];
+	} else if (args.includes("--deep-research")) {
+		depth = "deep";
+	} else if (args.includes("--synthesize")) {
+		depth = "standard";
+	}
+	// For "all" engine, default to standard if not specified
+	const engineArg = args.find((a) => !a.startsWith("--"))?.toLowerCase();
+	if (
+		engineArg === "all" &&
+		depthIdx === -1 &&
+		!args.includes("--deep-research") &&
+		!args.includes("--synthesize")
+	) {
+		depth = "standard";
+	}
+
+	const full = args.includes("--full") || depth === "deep";
 	const short = !full;
 	const fetchSource = args.includes("--fetch-top-source");
-	const synthesize =
-		args.includes("--synthesize") || args.includes("--deep-research");
-	const deepResearch = args.includes("--deep-research");
 	const inline = args.includes("--inline");
 	const outIdx = args.indexOf("--out");
 	const outFile = outIdx !== -1 ? args[outIdx + 1] : null;
@@ -1087,7 +1105,8 @@ async function main() {
 			a !== "--synthesize" &&
 			a !== "--deep-research" &&
 			a !== "--inline" &&
-			a !== "--out" &&
+			a !== "--depth" &&
+			(depthIdx === -1 || i !== depthIdx + 1) &&
 			(outIdx === -1 || i !== outIdx + 1),
 	);
 	const engine = rest[0].toLowerCase();
@@ -1137,7 +1156,7 @@ async function main() {
 			// Build a canonical source registry across all engines
 			out._sources = buildSourceRegistry(out);
 
-			if (deepResearch) {
+			if (depth === "deep") {
 				process.stderr.write("PROGRESS:deep-research:start\n");
 				const fetchedSources =
 					out._sources.length > 0
@@ -1153,8 +1172,8 @@ async function main() {
 				);
 			}
 
-			// Synthesize with Gemini if requested
-			if (synthesize) {
+			// Synthesize with Gemini for standard and deep modes
+			if (depth !== "fast") {
 				process.stderr.write("PROGRESS:synthesis:start\n");
 				process.stderr.write(
 					"[greedysearch] Synthesizing results with Gemini...\n",
@@ -1165,7 +1184,7 @@ async function main() {
 					tabs.push(geminiTab); // ensure cleanup in finally block
 					await activateTab(geminiTab);
 					const synthesis = await synthesizeWithGemini(query, out, {
-						grounded: deepResearch,
+						grounded: depth === "deep",
 						tabPrefix: geminiTab,
 					});
 					out._synthesis = {
@@ -1187,9 +1206,13 @@ async function main() {
 					out._topSource = await fetchTopSource(top.canonicalUrl || top.url);
 			}
 
-			if (deepResearch) out._confidence = buildConfidence(out);
+			if (depth === "deep") out._confidence = buildConfidence(out);
 
-			writeOutput(out, outFile, { inline, synthesize, query });
+			writeOutput(out, outFile, {
+				inline,
+				synthesize: depth !== "fast",
+				query,
+			});
 			return;
 		} finally {
 			await closeTabs(tabs);
@@ -1209,7 +1232,7 @@ async function main() {
 		if (fetchSource && result.sources?.length > 0) {
 			result.topSource = await fetchTopSource(result.sources[0].url);
 		}
-		writeOutput(result, outFile, { inline, synthesize, query });
+		writeOutput(result, outFile, { inline, synthesize: false, query });
 	} catch (e) {
 		process.stderr.write(`Error: ${e.message}\n`);
 		process.exit(1);

package/skills/greedy-search/SKILL.md

@@ -1,48 +1,57 @@
 ---
 name: greedy-search
-description: Multi-engine AI web search — greedy_search, deep_research, and coding_task. Use for high-quality research where training data may be stale or single-engine results are insufficient.
+description: Multi-engine AI web search — greedy_search with three depth levels (fast/standard/deep). Use for high-quality research where training data may be stale or single-engine results are insufficient. NO API KEYS needed.
 ---
 
 # GreedySearch Tools
 
 | Tool | Speed | Use For |
 |------|-------|---------|
-| `greedy_search` | 15-90s | Quick lookups, current info |
-| `deep_research` | 60-120s | Architecture decisions, source-backed research |
+| `greedy_search` | 15-180s | Multi-engine search with depth levels |
 | `coding_task` | 60-180s | Debug, review, plan modes for hard problems |
 
 ## greedy_search
 
-Multi-engine AI search (Perplexity, Bing, Google).
+Multi-engine AI search (Perplexity, Bing, Google) with three depth levels.
 
-```greedy_search({ query: "React 19 changes", engine: "all" })```
+```greedy_search({ query: "React 19 changes", depth: "standard" })```
 
 | Parameter | Type | Default | Description |
 |-----------|------|---------|-------------|
 | `query` | string | required | Search question |
 | `engine` | string | `"all"` | `all`, `perplexity`, `bing`, `google`, `gemini` |
-| `synthesize` | boolean | `false` | Gemini synthesis (+30s, higher quality) |
+| `depth` | string | `"standard"` | `fast`, `standard`, `deep` — see below |
 | `fullAnswer` | boolean | `false` | Complete vs ~300 char summary |
 
-**When to use:** Current info, version changes, comparisons, debugging errors.  
-**vs web_search:** Slower but higher quality — 3 engines cross-verify.
+### Depth Levels
 
-**Engine Selection:**
-- `all` (default): 30-90s, highest confidence
-- `perplexity`: 15-30s, technical Q&A
-- `bing`: 15-30s, recent news
-- `google`: 15-30s, broad coverage
-- `gemini`: 15-30s, different training data
+| Depth | Engines | Synthesis | Source Fetch | Time | Use When |
+|-------|---------|-----------|--------------|------|----------|
+| `fast` | 1 | ❌ | ❌ | 15-30s | Quick lookup, single perspective |
+| `standard` | 3 | ✅ | ❌ | 30-90s | Default — balanced speed/quality |
+| `deep` | 3 | ✅ | ✅ (top 5) | 60-180s | Research that matters — architecture decisions |
 
-## deep_research
+**Standard** (default): Runs 3 engines, deduplicates sources, synthesizes via Gemini.  
+**Deep**: Same + fetches content from top sources for grounded synthesis + confidence scores.
 
-Comprehensive research with source fetching and synthesis.
+### Engine Selection (for fast mode)
 
-```deep_research({ query: "RAG vs fine-tuning tradeoffs" })```
+```greedy_search({ query: "...", engine: "perplexity", depth: "fast" })```
 
-Returns: Full answers + Gemini synthesis + deduplicated sources (ranked by consensus [3/3, 2/3, 1/3]) + fetched content from top sources.
+- `perplexity`: Technical Q&A, citations
+- `bing`: Recent news, Microsoft ecosystem
+- `google`: Broad coverage
+- `gemini`: Different training data
 
-**When to use:** Research that matters — library comparisons, architecture decisions, source-backed confidence.
+### Examples
+
+```greedy_search({ query: "what changed in React 19", depth: "fast" })```
+```greedy_search({ query: "best auth patterns for SaaS", depth: "deep" })```
+```greedy_search({ query: "Prisma vs Drizzle 2026", depth: "standard", fullAnswer: true })```
+
+### Legacy
+
+`deep_research` tool still works — aliases to `greedy_search` with `depth: "deep"`.
 
 ## coding_task
 
@@ -58,17 +67,17 @@ Browser-based coding assistant via Gemini/Copilot.
 | `context` | string | — | Code snippet to include |
 
 **Modes:**
-- `debug`: Stuck on tricky bug — fresh eyes catch different failure modes
-- `plan`: Big refactor coming — Gemini plays devil's advocate
+- `debug`: Tricky bugs — fresh eyes catch different failure modes
+- `plan`: Big refactor — plays devil's advocate on risks
 - `review`: High-stakes code review before merge
 - `test`: Edge cases the author missed
 - `code`: Simple generation (but you're probably faster)
 
 **When to use:** Second opinions on hard problems. Skip for simple code.
 
-## Interpreting Results
+## Result Interpretation
 
-- **All 3 agree** → High confidence, present as fact
-- **2 agree, 1 differs** → Likely correct, note the dissent
-- **All differ** → Present different perspectives
-- **Sources [3/3] or [2/3]** → Cited by multiple engines, higher confidence
+- **All 3 engines agree** → High confidence, present as fact
+- **2 agree, 1 differs** → Likely correct, note dissent
+- **Sources [3/3] or [2/3]** → Multiple engines cite, higher confidence
+- **Deep research confidence scores** → Structured confidence metadata

package/.pi-lens/cache/jscpd.json

@@ -1,112 +0,0 @@
-{
-  "success": true,
-  "clones": [
-    {
-      "fileA": "extractors\\gemini.mjs",
-      "startA": 63,
-      "fileB": "extractors\\perplexity.mjs",
-      "startB": 34,
-      "lines": 20,
-      "tokens": 0
-    },
-    {
-      "fileA": "extractors\\gemini.mjs",
-      "startA": 82,
-      "fileB": "extractors\\google-ai.mjs",
-      "startB": 96,
-      "lines": 13,
-      "tokens": 0
-    },
-    {
-      "fileA": "extractors\\bing-copilot.mjs",
-      "startA": 44,
-      "fileB": "extractors\\gemini.mjs",
-      "startB": 60,
-      "lines": 24,
-      "tokens": 0
-    },
-    {
-      "fileA": "extractors\\bing-copilot.mjs",
-      "startA": 67,
-      "fileB": "extractors\\google-ai.mjs",
-      "startB": 96,
-      "lines": 13,
-      "tokens": 0
-    },
-    {
-      "fileA": "extractors\\bing-copilot.mjs",
-      "startA": 111,
-      "fileB": "extractors\\perplexity.mjs",
-      "startB": 74,
-      "lines": 8,
-      "tokens": 0
-    },
-    {
-      "fileA": "extractors\\bing-copilot.mjs",
-      "startA": 134,
-      "fileB": "extractors\\perplexity.mjs",
-      "startB": 85,
-      "lines": 7,
-      "tokens": 0
-    },
-    {
-      "fileA": "extractors\\bing-copilot.mjs",
-      "startA": 151,
-      "fileB": "extractors\\perplexity.mjs",
-      "startB": 110,
-      "lines": 17,
-      "tokens": 0
-    },
-    {
-      "fileA": "test.mjs",
-      "startA": 35,
-      "fileB": "extractors\\common.mjs",
-      "startB": 25,
-      "lines": 6,
-      "tokens": 0
-    },
-    {
-      "fileA": "index.ts",
-      "startA": 410,
-      "fileB": "index.ts",
-      "startB": 396,
-      "lines": 11,
-      "tokens": 0
-    },
-    {
-      "fileA": "index.ts",
-      "startA": 573,
-      "fileB": "index.ts",
-      "startB": 504,
-      "lines": 7,
-      "tokens": 0
-    },
-    {
-      "fileA": "index.ts",
-      "startA": 601,
-      "fileB": "index.ts",
-      "startB": 531,
-      "lines": 9,
-      "tokens": 0
-    },
-    {
-      "fileA": "index.ts",
-      "startA": 699,
-      "fileB": "index.ts",
-      "startB": 36,
-      "lines": 15,
-      "tokens": 0
-    },
-    {
-      "fileA": "coding-task.mjs",
-      "startA": 161,
-      "fileB": "coding-task.mjs",
-      "startB": 103,
-      "lines": 11,
-      "tokens": 0
-    }
-  ],
-  "duplicatedLines": 148,
-  "totalLines": 3187,
-  "percentage": 4.64
-}

package/.pi-lens/cache/jscpd.meta.json

@@ -1,3 +0,0 @@
-{
-  "timestamp": "2026-03-29T12:39:01.584Z"
-}