feat: implement M3.7.8 symptom projection (250 LOC) + 22 tests (10 unit + 12 integration)

IMPLEMENTATION: - crates/mem-core/src/symptom_projection.rs (250 LOC) - project_symptom(tool, query) → SymptomVector - Three-stage normalization: - Stage 1: Extract keywords - Stage 2: Normalize (stop words, abbreviations) - Stage 3: Generate deterministic SHA256 hash - Tool-specific abbreviation mappings (npm, cargo, kubectl, docker, go) - Stop words list (30+ common words) - Confidence scoring based on keyword specificity TEST COVERAGE: 22 tests passing - 10 unit tests in lib (determinism, abbreviations, stop words, tools, case, order) - 12 integration tests (a1-a6 assertions from design doc) - Real-world scenario tests (npm, cargo, kubectl) - 100% deterministic hashing verified INTEGRATION: - Module exported in crates/mem-core/src/lib.rs - All 43 existing mem-core tests still passing - Ready for M3.7.4 context endpoint integration DESIGN ASSERTIONS (all passing): ✅ a1: Same symptom = same hash (deterministic) ✅ a2: Abbreviation expansion (ERESOLVE → error resolve) ✅ a3: Stop word removal (is, unable, to, the) ✅ a4: Tool consistency (npm ≠ cargo for same error) ✅ a5: Case insensitive (NPM = npm) ✅ a6: Keyword order irrelevant (sorted before hash)
2026-08-28 08:08:55 -07:00
parent ad9cbe1fdc
commit 19967d1699
4 changed files with 957 additions and 0 deletions
@@ -0,0 +1,178 @@
+//! Integration tests for M3.7.8 symptom projection
+//! Tests the six main assertions from the design doc
+
+use mem_core::project_symptom;
+
+#[test]
+fn a1_same_symptom_same_hash() {
+    // ASSERTION 1: Same query always produces identical hash (deterministic)
+    let query = "npm ERR! ERESOLVE unable to resolve dependency tree";
+    
+    let sym1 = project_symptom("npm", query);
+    let sym2 = project_symptom("npm", query);
+    let sym3 = project_symptom("npm", query);
+
+    assert_eq!(sym1.sym_sha, sym2.sym_sha);
+    assert_eq!(sym2.sym_sha, sym3.sym_sha);
+    assert_eq!(sym1.sym_sha.len(), 64); // SHA256 = 64 hex chars
+}
+
+#[test]
+fn a2_abbrev_expansion() {
+    // ASSERTION 2: Tool-specific abbreviations expand correctly
+    // npm: ERESOLVE → error resolve
+    let npm_query = "npm ERESOLVE error";
+    let npm_sym = project_symptom("npm", npm_query);
+    assert!(npm_sym.normalised.contains("resolve"), "ERESOLVE should expand to 'resolve'");
+    
+    // cargo: E0599 → error 0599
+    let cargo_query = "cargo E0599 method";
+    let cargo_sym = project_symptom("cargo", cargo_query);
+    assert!(cargo_sym.normalised.contains("0599"), "E0599 should expand");
+    
+    // kubectl: CRD → custom resource definition
+    let kubectl_query = "error CRD";
+    let kubectl_sym = project_symptom("kubectl", kubectl_query);
+    assert!(kubectl_sym.normalised.contains("custom"), "CRD should expand to custom");
+}
+
+#[test]
+fn a3_stop_word_removal() {
+    // ASSERTION 3: Stop words removed (is, unable, to, the, of, etc.)
+    let query = "npm is unable to resolve the dependency";
+    let symptom = project_symptom("npm", query);
+    
+    // Stop words should not appear
+    assert!(!symptom.normalised.split_whitespace().any(|w| w == "is"));
+    assert!(!symptom.normalised.split_whitespace().any(|w| w == "unable"));
+    assert!(!symptom.normalised.split_whitespace().any(|w| w == "to"));
+    assert!(!symptom.normalised.split_whitespace().any(|w| w == "the"));
+    
+    // Content should remain
+    assert!(symptom.normalised.contains("npm"));
+    assert!(symptom.normalised.contains("resolve"));
+    assert!(symptom.normalised.contains("dependency"));
+}
+
+#[test]
+fn a4_tool_consistency() {
+    // ASSERTION 4: Tool name is part of identity
+    // Same query, different tools = different hashes
+    let query = "error 1234 module";
+    
+    let npm_sym = project_symptom("npm", query);
+    let cargo_sym = project_symptom("cargo", query);
+    let kubectl_sym = project_symptom("kubectl", query);
+    
+    assert_ne!(npm_sym.sym_sha, cargo_sym.sym_sha);
+    assert_ne!(cargo_sym.sym_sha, kubectl_sym.sym_sha);
+    assert_ne!(npm_sym.sym_sha, kubectl_sym.sym_sha);
+}
+
+#[test]
+fn a5_case_insensitive() {
+    // ASSERTION 5: Case doesn't affect hash
+    // (all normalized to lowercase)
+    let q1 = project_symptom("npm", "NPM ERROR ERESOLVE");
+    let q2 = project_symptom("npm", "npm error eresolve");
+    let q3 = project_symptom("npm", "NpM eRrOr ErEsOlVe");
+    
+    assert_eq!(q1.sym_sha, q2.sym_sha);
+    assert_eq!(q2.sym_sha, q3.sym_sha);
+}
+
+#[test]
+fn a6_keyword_order_irrelevant() {
+    // ASSERTION 6: Keyword order irrelevant
+    // (keywords sorted alphabetically before hashing)
+    let q1 = project_symptom("npm", "error npm resolve typescript");
+    let q2 = project_symptom("npm", "npm typescript resolve error");
+    let q3 = project_symptom("npm", "typescript error npm resolve");
+    
+    assert_eq!(q1.sym_sha, q2.sym_sha, "Different order should hash the same");
+    assert_eq!(q2.sym_sha, q3.sym_sha, "Different order should hash the same");
+    
+    // Verify keywords are sorted
+    let mut words: Vec<_> = q1.normalised.split_whitespace().collect();
+    words.sort();
+    let normalised_words: Vec<_> = q1.normalised.split_whitespace().collect();
+    assert_eq!(words, normalised_words, "Keywords should be sorted");
+}
+
+#[test]
+fn test_deterministic_across_calls() {
+    // Multiple calls with same query = identical results
+    let query = "npm unable to resolve typescript dependency";
+    let mut hashes = Vec::new();
+    
+    for _ in 0..10 {
+        let sym = project_symptom("npm", query);
+        hashes.push(sym.sym_sha);
+    }
+    
+    for hash in &hashes[1..] {
+        assert_eq!(hash, &hashes[0]);
+    }
+}
+
+#[test]
+fn test_real_world_npm() {
+    // Real npm error scenarios
+    let queries = vec![
+        "npm ERR! code ERESOLVE",
+        "npm ERR! ERESOLVE unable to resolve dependency tree",
+        "npm error cannot find module typescript",
+        "npm E404 not found",
+    ];
+    
+    for query in queries {
+        let sym = project_symptom("npm", query);
+        assert!(!sym.sym_sha.is_empty());
+        assert_eq!(sym.tool, "npm");
+        assert!(sym.confidence > 0.0);
+    }
+}
+
+#[test]
+fn test_real_world_cargo() {
+    // Real cargo error scenarios
+    let queries = vec![
+        "error E0599 no method found",
+        "error E0308 mismatched types",
+        "cargo error failed to compile",
+    ];
+    
+    for query in queries {
+        let sym = project_symptom("cargo", query);
+        assert!(!sym.sym_sha.is_empty());
+        assert_eq!(sym.tool, "cargo");
+    }
+}
+
+#[test]
+fn test_matches_signature() {
+    // SymptomVector::matches_signature works correctly
+    let sym = project_symptom("npm", "npm error resolve dependency");
+    
+    assert!(sym.matches_signature(&sym.sym_sha));
+    assert!(!sym.matches_signature("different_hash"));
+    assert!(!sym.matches_signature(&sym.sym_sha[0..32])); // partial hash
+}
+
+#[test]
+fn test_raw_query_preserved() {
+    // Original query should be preserved for logging
+    let original = "npm ERR! ERESOLVE unable to resolve typescript";
+    let sym = project_symptom("npm", original);
+    
+    assert_eq!(sym.raw_query, original);
+}
+
+#[test]
+fn test_confidence_scoring() {
+    // More specific queries = higher confidence
+    let low = project_symptom("npm", "error");
+    let high = project_symptom("npm", "npm error ERESOLVE cannot resolve typescript module");
+    
+    assert!(high.confidence >= low.confidence);
+}