sweet-search 2.6.15 → 2.6.16

package/core/prompt-optimization/data/p7-final/sweet-search-system-prompt-mcp.md

@@ -1,17 +1,21 @@
 ---
 variant: mcp
-derived_from: p7-v1-mpppp
-source_prompt: core/prompt-optimization/data/p7-variant-restarts/p7-gen3-candidates/Mpppp.md
+derived_from: p7-v1-mppppp
+source_prompt: core/prompt-optimization/data/p7-variant-restarts/p7-gen3-candidates/Mppppp.md
 benchmarked: false
 note: >-
-  Hand-derived MCP-tool variant of the M++++ champion (p7-v1-mpppp = M++ +
-  stop-discipline scoping edits: search-rules-only intro, "stop searching" /
-  "Search output" wording; routing unchanged from the frozen, benchmarked
-  M++). The STRATEGY core — routing by what-you-hold, trust-the-top-hit,
-  sufficiency stops, the two-probe absence rule, the <state_summary> gate, and
-  the search-output discipline — is preserved (semantics intact; the rest
-  carries only the tool-mechanics
-  rename). Only the tool-mechanics layer is remapped: the six ss-* CLI commands collapse onto the sweet-search MCP
+  Hand-derived MCP-tool variant of the M+++++ champion (p7-v1-mppppp = M++++ +
+  the verdict-gated trust line: trust rank 1 outright when the response
+  reports sufficiency yes, otherwise scan the already-delivered lower
+  ranks/same-file map before any new search; smoke-validated on the
+  task-completion bench, see memory
+  project_mppppp_conditional_trust_candidate). The STRATEGY core — routing by
+  what-you-hold, verdict-gated trust, sufficiency stops, the two-probe absence
+  rule, the <state_summary> gate, and the search-output discipline — is
+  preserved (semantics intact; the rest carries only the tool-mechanics
+  rename). The trust gate is phrased against the MCP response surface
+  (sufficiency verdict in structured content; "Also found" summary list;
+  "Same file:" map line) instead of the CLI sufficient= trailer. Only the tool-mechanics layer is remapped: the six ss-* CLI commands collapse onto the sweet-search MCP
   tool surface (a UNIFIED `search` that subsumes ss-search/ss-find/ss-grep, plus
   `trace` / `read-semantic` / `read` / `repo-map`). The anti-raw-scan discipline
   is KEPT and retargeted from "ss-* vs raw grep" to "sweet-search tools vs native
@@ -40,7 +44,7 @@ The sweet-search MCP server exposes these (call each by the name your client lis
 - **Only a behavior or concept**: one `search` in natural language for what you're looking for, then anchor on the symbol that surfaces. Shape it lightly by the target language — short and interrogative for JS/TS/Dart, a touch longer with a domain keyword otherwise.
 - **How something flows / dispatches / is called / what a change impacts**: anchor one symbol (a literal, or a `search`), then `trace` it — one call returns callers, callees and impact. Prefer callees over impact (especially Python/Ruby/PHP). If a trace is sparse or empty, anchor the downstream symbol with `search` rather than retrying or hand-crawling; never make `trace` the spine of a multi-file search.
 
-Trust the top ranked result; confirm with at most one narrow `read`, never a re-run of a matching hit.
+When the response reports sufficiency `yes`, trust the top ranked result outright; confirm with at most one narrow `read`, never a re-run of a matching hit. Otherwise, scan the rest of the results you already have (lower ranks, the `Also found` list, the `Same file:` line) before issuing any new search — the winner is often rank 2-3.
 
 ## Multi-file
 Chain inside the tools: land the entry file, `read-semantic` it for the import or handoff symbol, then `search` the downstream module. The trace is COMPLETE the moment you can name the link from the entry symbol to the thing it reaches; stop tracing there. Leaf bodies, macro expansions, and the next hop down are not the answer unless asked, and chasing them — or dropping to a native Grep/Read to "just look" — is the main multi-file cost trap.

package/core/prompt-optimization/data/p7-final/sweet-search-system-prompt.md

@@ -1,12 +1,12 @@
 ---
-run_id: p7-v1-mpppp
+run_id: p7-v1-mppppp
 score_sonnet: 0.993
 score_gpt5_5: 0.988
 joint_maximin: 0.988
 eas_factor: null
 length_penalty: null
 final_score: null
-token_count: 1175
+token_count: 1221
 scs_cwSCS: 0.931
 scs_min_paraphrase_accuracy: 1
 homp_family_pass: true
@@ -37,7 +37,7 @@ Sweet-search indexes the working tree (uncommitted edits too) and searches it fa
 - **Only a behavior or concept**: one `ss-search` in natural language for what you're looking for, then anchor on the symbol that surfaces. Shape it lightly by the target language — short and interrogative for JS/TS/Dart, a touch longer with a domain keyword otherwise.
 - **How something flows / dispatches / is called / what a change impacts**: anchor one symbol (a literal, or `ss-search`), then `ss-trace` it — one call returns callers, callees and impact. Prefer callees over impact (especially Python/Ruby/PHP). If a trace is sparse or empty, anchor the downstream symbol with `ss-find`/`ss-search` rather than retrying or hand-crawling; never make `ss-trace` the spine of a multi-file search.
 
-Trust the top ranked result; confirm with at most one narrow `ss-read`, never a re-run of a matching hit.
+On `sufficient=YES`, trust the top ranked result outright; confirm with at most one narrow `ss-read`, never a re-run of a matching hit. Otherwise, scan the rest of the pack you already have (lower ranks, the `same file:` line) before issuing any new search — the winner is often rank 2-3.
 
 ## Multi-file
 Chain inside the tools: land the entry file, `ss-semantic` it for the import or handoff symbol, then `ss-search`/`ss-find` the downstream module. The trace is COMPLETE the moment you can name the link from the entry symbol to the thing it reaches; stop tracing there. Leaf bodies, macro expansions, and the next hop down are not the answer unless asked, and chasing them — or dropping to raw `cat`/`grep` to "just look" — is the main multi-file cost trap.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sweet-search",
-  "version": "2.6.15",
+  "version": "2.6.16",
   "description": "Sweet Search - SOTA Hybrid Code Search Engine with WASM CatBoost Query Router, Semantic/Lexical/Structural Search, and Multilingual Support",
   "type": "module",
   "main": "core/search/sweet-search.js",
@@ -167,13 +167,13 @@
     "vitest": "^4.0.16"
   },
   "optionalDependencies": {
-    "@sweet-search/native-darwin-arm64": "2.6.15",
-    "@sweet-search/native-darwin-x64": "2.6.15",
-    "@sweet-search/native-linux-arm64-gnu": "2.6.15",
-    "@sweet-search/native-linux-arm64-gnu-cuda": "2.6.15",
-    "@sweet-search/native-linux-x64-gnu": "2.6.15",
-    "@sweet-search/native-linux-x64-gnu-cuda": "2.6.15",
-    "@sweet-search/bg-priority": "2.6.15"
+    "@sweet-search/native-darwin-arm64": "2.6.16",
+    "@sweet-search/native-darwin-x64": "2.6.16",
+    "@sweet-search/native-linux-arm64-gnu": "2.6.16",
+    "@sweet-search/native-linux-arm64-gnu-cuda": "2.6.16",
+    "@sweet-search/native-linux-x64-gnu": "2.6.16",
+    "@sweet-search/native-linux-x64-gnu-cuda": "2.6.16",
+    "@sweet-search/bg-priority": "2.6.16"
   },
   "engines": {
     "node": ">=18.0.0"

package/scripts/inject-agent-instructions.js

@@ -46,18 +46,20 @@ function escapeRegex(s) {
   return s.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
 }
 
-// ─── Canonical policy body = the M++++ champion (integration seam) ───────────
+// ─── Canonical policy body = the M+++++ champion (integration seam) ──────────
 //
 // Plan §10 / §3.7.1 step 13 / DDD "Integration seam": scripts/init.js is the
 // SOLE consumer of the prompt-optimization ship-file. We read that artifact at
-// load time and strip its YAML front-matter; the remaining body is the M++++
+// load time and strip its YAML front-matter; the remaining body is the M+++++
 // champion (PHASE7 M++ — held-out 0.988 Maximin, OOD 0.952, HOMP/SCS/counter
 // all pass, 5-cell cross-harness validated — plus the stop-discipline scoping
-// edits that fix M++'s over-stopping on FIX tasks; routing unchanged),
-// injected VERBATIM into the harness files. Per-harness shims
-// (Cursor frontmatter, @imports) are applied at write-time, not embedded here.
+// edits that fix M++'s over-stopping on FIX tasks, plus the verdict-gated
+// trust line that scans already-delivered lower ranks before any new search;
+// tool routing unchanged), injected VERBATIM into the harness files.
+// Per-harness shims (Cursor frontmatter, @imports) are applied at write-time,
+// not embedded here.
 //
-// The artifact is generated from Mpppp.md by
+// The artifact is generated from Mppppp.md by
 // `core/prompt-optimization/sweep/finalize-mpp.mjs` and shipped via the
 // package.json "files" list. If it is missing we fail LOUDLY rather than
 // silently shipping a placeholder/older policy.
@@ -76,7 +78,7 @@ export function stripFrontMatter(text) {
   return text.replace(/^---\r?\n[\s\S]*?\r?\n---\r?\n/, '');
 }
 
-function readShippedPolicy(rel = SHIP_FILE_REL, { label = 'M++++' } = {}) {
+function readShippedPolicy(rel = SHIP_FILE_REL, { label = 'M+++++' } = {}) {
   const here = dirname(fileURLToPath(import.meta.url)); // <pkg>/scripts
   const shipPath = join(here, '..', rel);
   let raw;
@@ -103,7 +105,7 @@ let _mcpPolicyBody = null;
 /** Lazily read + cache the MCP-variant policy body. */
 export function getMcpPolicyBody() {
   if (_mcpPolicyBody == null) {
-    _mcpPolicyBody = readShippedPolicy(MCP_SHIP_FILE_REL, { label: 'M++++ (MCP variant)' });
+    _mcpPolicyBody = readShippedPolicy(MCP_SHIP_FILE_REL, { label: 'M+++++ (MCP variant)' });
   }
   return _mcpPolicyBody;
 }