@massa-ai/opencode-plugin 1.31.0 → 1.33.0

package/agent-profiles/balanced/massa-ai-audit-specialist.md

@@ -35,12 +35,13 @@ The `lens` field in the capability packet selects the audit behavior:
 | `requirements` | Requirements, spec, acceptance, scope alignment | `workflows/requirements/requirements-audit.md` |
 | `code-quality` | SOLID, Clean Code, KISS, YAGNI, DRY, maintainability | `workflows/code-quality/code-quality-audit.md` |
 | `performance` | Performance hotspots, allocation, latency, throughput | Domain-specific; no fixed reference |
+| `tests` | Coverage, regression protection, assertion quality, variation | `workflows/tests/tests-audit.md` |
 
 All lenses share `references/audit-scope.md` (scope rules) and `references/audit-report-io.md` (report format).
 
 ## Inputs
 - `scope`: the target area, diff, or module to audit.
-- `lens`: one of `bugs | architecture | security | requirements | code-quality | performance` (required).
+- `lens`: one of `bugs | architecture | security | requirements | code-quality | performance | tests` (required).
 - `inputs`: recalled facts, existing audit reports, source pointers.
 - `sensors`: static checks available for the lens (lint, typecheck, security scanners).
 

package/agent-profiles/balanced/massa-ai-test-engineer.md

@@ -9,12 +9,13 @@ permission: { edit: allow, bash: allow }
 # Test Engineer Agent Skill
 
 ## Mission
-Generate a testing strategy that covers unit, integration, edge cases, negative scenarios, and acceptance criteria.
+Generate a testing strategy that covers unit, integration, edge cases, negative scenarios, and acceptance criteria, and that catches the five distinct error classes a test suite must cover: business-logic errors, code no test touched, hardcoded-example brittleness, built-the-wrong-thing, and drift over time.
 
 ## Responsibilities
 - Define unit test cases for core logic.
 - Define integration test cases for boundaries.
 - Identify edge cases and negative scenarios.
+- Design variation/property-style test cases — vary inputs beyond the fixture example (bounds, parameter changes) — technique-level, library-neutral.
 - Produce a test plan aligned with acceptance criteria.
 - Ensure acceptance coverage maps to spec criteria.
 

package/agent-profiles/cheap/massa-ai-audit-specialist.md

@@ -35,12 +35,13 @@ The `lens` field in the capability packet selects the audit behavior:
 | `requirements` | Requirements, spec, acceptance, scope alignment | `workflows/requirements/requirements-audit.md` |
 | `code-quality` | SOLID, Clean Code, KISS, YAGNI, DRY, maintainability | `workflows/code-quality/code-quality-audit.md` |
 | `performance` | Performance hotspots, allocation, latency, throughput | Domain-specific; no fixed reference |
+| `tests` | Coverage, regression protection, assertion quality, variation | `workflows/tests/tests-audit.md` |
 
 All lenses share `references/audit-scope.md` (scope rules) and `references/audit-report-io.md` (report format).
 
 ## Inputs
 - `scope`: the target area, diff, or module to audit.
-- `lens`: one of `bugs | architecture | security | requirements | code-quality | performance` (required).
+- `lens`: one of `bugs | architecture | security | requirements | code-quality | performance | tests` (required).
 - `inputs`: recalled facts, existing audit reports, source pointers.
 - `sensors`: static checks available for the lens (lint, typecheck, security scanners).
 

package/agent-profiles/cheap/massa-ai-test-engineer.md

@@ -9,12 +9,13 @@ permission: { edit: allow, bash: allow }
 # Test Engineer Agent Skill
 
 ## Mission
-Generate a testing strategy that covers unit, integration, edge cases, negative scenarios, and acceptance criteria.
+Generate a testing strategy that covers unit, integration, edge cases, negative scenarios, and acceptance criteria, and that catches the five distinct error classes a test suite must cover: business-logic errors, code no test touched, hardcoded-example brittleness, built-the-wrong-thing, and drift over time.
 
 ## Responsibilities
 - Define unit test cases for core logic.
 - Define integration test cases for boundaries.
 - Identify edge cases and negative scenarios.
+- Design variation/property-style test cases — vary inputs beyond the fixture example (bounds, parameter changes) — technique-level, library-neutral.
 - Produce a test plan aligned with acceptance criteria.
 - Ensure acceptance coverage maps to spec criteria.
 

package/agent-profiles/heavy/massa-ai-audit-specialist.md

@@ -35,12 +35,13 @@ The `lens` field in the capability packet selects the audit behavior:
 | `requirements` | Requirements, spec, acceptance, scope alignment | `workflows/requirements/requirements-audit.md` |
 | `code-quality` | SOLID, Clean Code, KISS, YAGNI, DRY, maintainability | `workflows/code-quality/code-quality-audit.md` |
 | `performance` | Performance hotspots, allocation, latency, throughput | Domain-specific; no fixed reference |
+| `tests` | Coverage, regression protection, assertion quality, variation | `workflows/tests/tests-audit.md` |
 
 All lenses share `references/audit-scope.md` (scope rules) and `references/audit-report-io.md` (report format).
 
 ## Inputs
 - `scope`: the target area, diff, or module to audit.
-- `lens`: one of `bugs | architecture | security | requirements | code-quality | performance` (required).
+- `lens`: one of `bugs | architecture | security | requirements | code-quality | performance | tests` (required).
 - `inputs`: recalled facts, existing audit reports, source pointers.
 - `sensors`: static checks available for the lens (lint, typecheck, security scanners).
 

package/agent-profiles/heavy/massa-ai-test-engineer.md

@@ -9,12 +9,13 @@ permission: { edit: allow, bash: allow }
 # Test Engineer Agent Skill
 
 ## Mission
-Generate a testing strategy that covers unit, integration, edge cases, negative scenarios, and acceptance criteria.
+Generate a testing strategy that covers unit, integration, edge cases, negative scenarios, and acceptance criteria, and that catches the five distinct error classes a test suite must cover: business-logic errors, code no test touched, hardcoded-example brittleness, built-the-wrong-thing, and drift over time.
 
 ## Responsibilities
 - Define unit test cases for core logic.
 - Define integration test cases for boundaries.
 - Identify edge cases and negative scenarios.
+- Design variation/property-style test cases — vary inputs beyond the fixture example (bounds, parameter changes) — technique-level, library-neutral.
 - Produce a test plan aligned with acceptance criteria.
 - Ensure acceptance coverage maps to spec criteria.
 

package/agent-profiles/home/massa-ai-audit-specialist.md

@@ -35,12 +35,13 @@ The `lens` field in the capability packet selects the audit behavior:
 | `requirements` | Requirements, spec, acceptance, scope alignment | `workflows/requirements/requirements-audit.md` |
 | `code-quality` | SOLID, Clean Code, KISS, YAGNI, DRY, maintainability | `workflows/code-quality/code-quality-audit.md` |
 | `performance` | Performance hotspots, allocation, latency, throughput | Domain-specific; no fixed reference |
+| `tests` | Coverage, regression protection, assertion quality, variation | `workflows/tests/tests-audit.md` |
 
 All lenses share `references/audit-scope.md` (scope rules) and `references/audit-report-io.md` (report format).
 
 ## Inputs
 - `scope`: the target area, diff, or module to audit.
-- `lens`: one of `bugs | architecture | security | requirements | code-quality | performance` (required).
+- `lens`: one of `bugs | architecture | security | requirements | code-quality | performance | tests` (required).
 - `inputs`: recalled facts, existing audit reports, source pointers.
 - `sensors`: static checks available for the lens (lint, typecheck, security scanners).
 

package/agent-profiles/home/massa-ai-test-engineer.md

@@ -9,12 +9,13 @@ permission: { edit: allow, bash: allow }
 # Test Engineer Agent Skill
 
 ## Mission
-Generate a testing strategy that covers unit, integration, edge cases, negative scenarios, and acceptance criteria.
+Generate a testing strategy that covers unit, integration, edge cases, negative scenarios, and acceptance criteria, and that catches the five distinct error classes a test suite must cover: business-logic errors, code no test touched, hardcoded-example brittleness, built-the-wrong-thing, and drift over time.
 
 ## Responsibilities
 - Define unit test cases for core logic.
 - Define integration test cases for boundaries.
 - Identify edge cases and negative scenarios.
+- Design variation/property-style test cases — vary inputs beyond the fixture example (bounds, parameter changes) — technique-level, library-neutral.
 - Produce a test plan aligned with acceptance criteria.
 - Ensure acceptance coverage maps to spec criteria.
 

package/agent-profiles/local_models/massa-ai-audit-specialist.md

@@ -35,12 +35,13 @@ The `lens` field in the capability packet selects the audit behavior:
 | `requirements` | Requirements, spec, acceptance, scope alignment | `workflows/requirements/requirements-audit.md` |
 | `code-quality` | SOLID, Clean Code, KISS, YAGNI, DRY, maintainability | `workflows/code-quality/code-quality-audit.md` |
 | `performance` | Performance hotspots, allocation, latency, throughput | Domain-specific; no fixed reference |
+| `tests` | Coverage, regression protection, assertion quality, variation | `workflows/tests/tests-audit.md` |
 
 All lenses share `references/audit-scope.md` (scope rules) and `references/audit-report-io.md` (report format).
 
 ## Inputs
 - `scope`: the target area, diff, or module to audit.
-- `lens`: one of `bugs | architecture | security | requirements | code-quality | performance` (required).
+- `lens`: one of `bugs | architecture | security | requirements | code-quality | performance | tests` (required).
 - `inputs`: recalled facts, existing audit reports, source pointers.
 - `sensors`: static checks available for the lens (lint, typecheck, security scanners).
 

package/agent-profiles/local_models/massa-ai-test-engineer.md

@@ -9,12 +9,13 @@ permission: { edit: allow, bash: allow }
 # Test Engineer Agent Skill
 
 ## Mission
-Generate a testing strategy that covers unit, integration, edge cases, negative scenarios, and acceptance criteria.
+Generate a testing strategy that covers unit, integration, edge cases, negative scenarios, and acceptance criteria, and that catches the five distinct error classes a test suite must cover: business-logic errors, code no test touched, hardcoded-example brittleness, built-the-wrong-thing, and drift over time.
 
 ## Responsibilities
 - Define unit test cases for core logic.
 - Define integration test cases for boundaries.
 - Identify edge cases and negative scenarios.
+- Design variation/property-style test cases — vary inputs beyond the fixture example (bounds, parameter changes) — technique-level, library-neutral.
 - Produce a test plan aligned with acceptance criteria.
 - Ensure acceptance coverage maps to spec criteria.
 

package/agent-profiles/open_models/massa-ai-audit-specialist.md

@@ -35,12 +35,13 @@ The `lens` field in the capability packet selects the audit behavior:
 | `requirements` | Requirements, spec, acceptance, scope alignment | `workflows/requirements/requirements-audit.md` |
 | `code-quality` | SOLID, Clean Code, KISS, YAGNI, DRY, maintainability | `workflows/code-quality/code-quality-audit.md` |
 | `performance` | Performance hotspots, allocation, latency, throughput | Domain-specific; no fixed reference |
+| `tests` | Coverage, regression protection, assertion quality, variation | `workflows/tests/tests-audit.md` |
 
 All lenses share `references/audit-scope.md` (scope rules) and `references/audit-report-io.md` (report format).
 
 ## Inputs
 - `scope`: the target area, diff, or module to audit.
-- `lens`: one of `bugs | architecture | security | requirements | code-quality | performance` (required).
+- `lens`: one of `bugs | architecture | security | requirements | code-quality | performance | tests` (required).
 - `inputs`: recalled facts, existing audit reports, source pointers.
 - `sensors`: static checks available for the lens (lint, typecheck, security scanners).
 

package/agent-profiles/open_models/massa-ai-test-engineer.md

@@ -9,12 +9,13 @@ permission: { edit: allow, bash: allow }
 # Test Engineer Agent Skill
 
 ## Mission
-Generate a testing strategy that covers unit, integration, edge cases, negative scenarios, and acceptance criteria.
+Generate a testing strategy that covers unit, integration, edge cases, negative scenarios, and acceptance criteria, and that catches the five distinct error classes a test suite must cover: business-logic errors, code no test touched, hardcoded-example brittleness, built-the-wrong-thing, and drift over time.
 
 ## Responsibilities
 - Define unit test cases for core logic.
 - Define integration test cases for boundaries.
 - Identify edge cases and negative scenarios.
+- Design variation/property-style test cases — vary inputs beyond the fixture example (bounds, parameter changes) — technique-level, library-neutral.
 - Produce a test plan aligned with acceptance criteria.
 - Ensure acceptance coverage maps to spec criteria.
 

package/agent-profiles/work/massa-ai-audit-specialist.md

@@ -35,12 +35,13 @@ The `lens` field in the capability packet selects the audit behavior:
 | `requirements` | Requirements, spec, acceptance, scope alignment | `workflows/requirements/requirements-audit.md` |
 | `code-quality` | SOLID, Clean Code, KISS, YAGNI, DRY, maintainability | `workflows/code-quality/code-quality-audit.md` |
 | `performance` | Performance hotspots, allocation, latency, throughput | Domain-specific; no fixed reference |
+| `tests` | Coverage, regression protection, assertion quality, variation | `workflows/tests/tests-audit.md` |
 
 All lenses share `references/audit-scope.md` (scope rules) and `references/audit-report-io.md` (report format).
 
 ## Inputs
 - `scope`: the target area, diff, or module to audit.
-- `lens`: one of `bugs | architecture | security | requirements | code-quality | performance` (required).
+- `lens`: one of `bugs | architecture | security | requirements | code-quality | performance | tests` (required).
 - `inputs`: recalled facts, existing audit reports, source pointers.
 - `sensors`: static checks available for the lens (lint, typecheck, security scanners).
 

package/agent-profiles/work/massa-ai-test-engineer.md

@@ -9,12 +9,13 @@ permission: { edit: allow, bash: allow }
 # Test Engineer Agent Skill
 
 ## Mission
-Generate a testing strategy that covers unit, integration, edge cases, negative scenarios, and acceptance criteria.
+Generate a testing strategy that covers unit, integration, edge cases, negative scenarios, and acceptance criteria, and that catches the five distinct error classes a test suite must cover: business-logic errors, code no test touched, hardcoded-example brittleness, built-the-wrong-thing, and drift over time.
 
 ## Responsibilities
 - Define unit test cases for core logic.
 - Define integration test cases for boundaries.
 - Identify edge cases and negative scenarios.
+- Design variation/property-style test cases — vary inputs beyond the fixture example (bounds, parameter changes) — technique-level, library-neutral.
 - Produce a test plan aligned with acceptance criteria.
 - Ensure acceptance coverage maps to spec criteria.
 

package/agents/massa-ai-audit-specialist.md

@@ -35,12 +35,13 @@ The `lens` field in the capability packet selects the audit behavior:
 | `requirements` | Requirements, spec, acceptance, scope alignment | `workflows/requirements/requirements-audit.md` |
 | `code-quality` | SOLID, Clean Code, KISS, YAGNI, DRY, maintainability | `workflows/code-quality/code-quality-audit.md` |
 | `performance` | Performance hotspots, allocation, latency, throughput | Domain-specific; no fixed reference |
+| `tests` | Coverage, regression protection, assertion quality, variation | `workflows/tests/tests-audit.md` |
 
 All lenses share `references/audit-scope.md` (scope rules) and `references/audit-report-io.md` (report format).
 
 ## Inputs
 - `scope`: the target area, diff, or module to audit.
-- `lens`: one of `bugs | architecture | security | requirements | code-quality | performance` (required).
+- `lens`: one of `bugs | architecture | security | requirements | code-quality | performance | tests` (required).
 - `inputs`: recalled facts, existing audit reports, source pointers.
 - `sensors`: static checks available for the lens (lint, typecheck, security scanners).
 

package/agents/massa-ai-test-engineer.md

@@ -9,12 +9,13 @@ permission: { edit: allow, bash: allow }
 # Test Engineer Agent Skill
 
 ## Mission
-Generate a testing strategy that covers unit, integration, edge cases, negative scenarios, and acceptance criteria.
+Generate a testing strategy that covers unit, integration, edge cases, negative scenarios, and acceptance criteria, and that catches the five distinct error classes a test suite must cover: business-logic errors, code no test touched, hardcoded-example brittleness, built-the-wrong-thing, and drift over time.
 
 ## Responsibilities
 - Define unit test cases for core logic.
 - Define integration test cases for boundaries.
 - Identify edge cases and negative scenarios.
+- Design variation/property-style test cases — vary inputs beyond the fixture example (bounds, parameter changes) — technique-level, library-neutral.
 - Produce a test plan aligned with acceptance criteria.
 - Ensure acceptance coverage maps to spec criteria.
 

package/dist/config-cli.js

@@ -410,9 +410,9 @@ var init_massa_ai_config = __esm(() => {
     },
     embedding: {
       provider: "ollama",
-      model: "nomic-embed-text:latest",
+      model: "qwen3-embedding:4b",
       baseURL: "http://localhost:11434",
-      dimensions: 768
+      dimensions: 2560
     },
     compression: {
       defaultStrategy: "code_structure",

package/dist/index.js

@@ -409,9 +409,9 @@ var init_massa_ai_config = __esm(() => {
     },
     embedding: {
       provider: "ollama",
-      model: "nomic-embed-text:latest",
+      model: "qwen3-embedding:4b",
       baseURL: "http://localhost:11434",
-      dimensions: 768
+      dimensions: 2560
     },
     compression: {
       defaultStrategy: "code_structure",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@massa-ai/opencode-plugin",
-  "version": "1.31.0",
+  "version": "1.33.0",
   "description": "massa-ai plugin for OpenCode - Semantic code search, memory, and context compression",
   "type": "module",
   "main": "dist/index.js",
@@ -23,8 +23,8 @@
   "dependencies": {
     "@opencode-ai/plugin": "^1.2.15",
     "@opencode-ai/sdk": "^1.2.15",
-    "@massa-ai/core": "^1.31.0",
-    "@massa-ai/shared": "^1.31.0"
+    "@massa-ai/core": "^1.33.0",
+    "@massa-ai/shared": "^1.33.0"
   },
   "devDependencies": {
     "@types/node": "^22.10.5",