🎮 GameObject Toolset Redesign and Streamlining

.claude/prompts/nl-gameobject-suite.md

@@ -0,0 +1,150 @@
+# Unity GameObject API Test Suite — Tool/Resource Separation
+
+You are running inside CI for the `unity-mcp` repo. Use only the tools allowed by the workflow. Work autonomously; do not prompt the user. Do NOT spawn subagents.
+
+**Print this once, verbatim, early in the run:**
+AllowedTools: Write,mcp__UnityMCP__manage_editor,mcp__UnityMCP__manage_gameobject,mcp__UnityMCP__find_gameobjects,mcp__UnityMCP__manage_components,mcp__UnityMCP__manage_scene,mcp__UnityMCP__read_console
+
+---
+
+## Mission
+1) Test the new Tool/Resource separation for GameObject management
+2) Execute GO tests GO-0..GO-10 in order
+3) Verify deprecation warnings appear for legacy actions
+4) **Report**: write one `<testcase>` XML fragment per test to `reports/<TESTID>_results.xml`
+
+**CRITICAL XML FORMAT REQUIREMENTS:**
+- Each file must contain EXACTLY one `<testcase>` root element
+- NO prologue, epilogue, code fences, or extra characters
+- Use this exact shape:
+
+<testcase name="GO-0 — Hierarchy with ComponentTypes" classname="UnityMCP.GO-T">
+  <system-out><![CDATA[
+(evidence of what was accomplished)
+  ]]></system-out>
+</testcase>
+
+- If test fails, include: `<failure message="reason"/>`
+- TESTID must be one of: GO-0, GO-1, GO-2, GO-3, GO-4, GO-5, GO-6, GO-7, GO-8, GO-9, GO-10
+
+---
+
+## Test Specs
+
+### GO-0. Hierarchy with ComponentTypes
+**Goal**: Verify get_hierarchy now includes componentTypes list
+**Actions**:
+- Call `mcp__UnityMCP__manage_scene(action="get_hierarchy", page_size=10)`
+- Verify response includes `componentTypes` array for each item in `data.items`
+- Check that Main Camera (or similar) has component types like `["Transform", "Camera", "AudioListener"]`
+- **Pass criteria**: componentTypes present and non-empty for at least one item
+
+### GO-1. Find GameObjects Tool
+**Goal**: Test the new find_gameobjects tool
+**Actions**:
+- Call `mcp__UnityMCP__find_gameobjects(search_term="Camera", search_method="by_component")`
+- Verify response contains `instanceIDs` array in `data`
+- Verify response contains pagination info (`pageSize`, `cursor`, `totalCount`)
+- **Pass criteria**: Returns at least one instance ID
+
+### GO-2. GameObject Resource Read
+**Goal**: Test reading a single GameObject via resource
+**Actions**:
+- Use the instance ID from GO-1
+- Call `mcp__UnityMCP__read_resource(uri="unity://scene/gameobject/{instanceID}")` replacing {instanceID} with the actual ID
+- Verify response includes: instanceID, name, tag, layer, transform, path
+- **Pass criteria**: All expected fields present
+
+### GO-3. Components Resource Read  
+**Goal**: Test reading components via resource
+**Actions**:
+- Use the instance ID from GO-1
+- Call `mcp__UnityMCP__read_resource(uri="unity://scene/gameobject/{instanceID}/components")` replacing {instanceID} with the actual ID
+- Verify response includes paginated component list in `data.items`
+- Verify at least one component has typeName and instanceID
+- **Pass criteria**: Components list returned with proper pagination
+
+### GO-4. Manage Components Tool - Add and Set Property
+**Goal**: Test the new manage_components tool (add component, set property)
+**Actions**:
+- Create a test GameObject: `mcp__UnityMCP__manage_gameobject(action="create", name="GO_Test_Object")`
+- Add a component: `mcp__UnityMCP__manage_components(action="add", target="GO_Test_Object", component_type="Rigidbody")`
+- Set a property: `mcp__UnityMCP__manage_components(action="set_property", target="GO_Test_Object", component_type="Rigidbody", properties={"mass": 5.0})`
+- Verify the component was added and property was set
+- **Pass criteria**: Component added, property set successfully
+- **Note**: Keep GO_Test_Object for GO-5 through GO-8
+
+### GO-5. Find GameObjects by Name
+**Goal**: Test find_gameobjects with by_name search method
+**Actions**:
+- Call `mcp__UnityMCP__find_gameobjects(search_term="GO_Test_Object", search_method="by_name")`
+- Verify response contains the GameObject created in GO-4
+- Verify pagination info is present
+- **Pass criteria**: Returns at least one instance ID matching GO_Test_Object
+
+### GO-6. Find GameObjects by Tag
+**Goal**: Test find_gameobjects with by_tag search method
+**Actions**:
+- Set a tag on GO_Test_Object: `mcp__UnityMCP__manage_gameobject(action="modify", target="GO_Test_Object", tag="TestTag")`
+- Call `mcp__UnityMCP__find_gameobjects(search_term="TestTag", search_method="by_tag")`
+- Verify response contains the tagged GameObject
+- **Pass criteria**: Returns at least one instance ID
+
+### GO-7. Single Component Resource Read
+**Goal**: Test reading a single component via resource
+**Actions**:
+- Get instance ID of GO_Test_Object from GO-5
+- Call `mcp__UnityMCP__read_resource(uri="unity://scene/gameobject/{instanceID}/component/Rigidbody")` replacing {instanceID}
+- Verify response includes component data with typeName="Rigidbody"
+- Verify mass property is 5.0 (set in GO-4)
+- **Pass criteria**: Component data returned with correct properties
+
+### GO-8. Remove Component
+**Goal**: Test manage_components remove action
+**Actions**:
+- Remove the Rigidbody from GO_Test_Object: `mcp__UnityMCP__manage_components(action="remove", target="GO_Test_Object", component_type="Rigidbody")`
+- Verify the component was removed by attempting to read it again
+- **Pass criteria**: Component successfully removed
+
+### GO-9. Find with Pagination
+**Goal**: Test find_gameobjects pagination
+**Actions**:
+- Call `mcp__UnityMCP__find_gameobjects(search_term="", search_method="by_name", page_size=2)`
+- Verify response includes cursor for next page
+- If cursor is present, call again with the cursor to get next page
+- Clean up: `mcp__UnityMCP__manage_gameobject(action="delete", target="GO_Test_Object")`
+- **Pass criteria**: Pagination works (cursor present when more results available)
+
+### GO-10. Deprecation Warnings
+**Goal**: Verify legacy actions log deprecation warnings
+**Actions**:
+- Call legacy action: `mcp__UnityMCP__manage_gameobject(action="find", search_term="Camera", search_method="by_component")`
+- Read console using `mcp__UnityMCP__read_console` for deprecation warning
+- Verify warning mentions "find_gameobjects" as replacement
+- **Pass criteria**: Deprecation warning logged
+
+---
+
+## Tool Reference
+
+### New Tools
+- `find_gameobjects(search_term, search_method, page_size?, cursor?, search_inactive?)` - Returns instance IDs only
+- `manage_components(action, target, component_type?, properties?)` - Add/remove/set_property/get_all/get_single
+
+### New Resources  
+- `unity://scene/gameobject/{instanceID}` - Single GameObject data
+- `unity://scene/gameobject/{instanceID}/components` - All components (paginated)
+- `unity://scene/gameobject/{instanceID}/component/{componentName}` - Single component
+
+### Updated Resources
+- `manage_scene(action="get_hierarchy")` - Now includes `componentTypes` array in each item
+
+---
+
+## Transcript Minimization Rules
+- Do not restate tool JSON; summarize in ≤ 2 short lines
+- Per-test `system-out` ≤ 400 chars
+- Console evidence: include ≤ 3 lines in the fragment
+
+---
+

.claude/prompts/nl-unity-suite-nl.md

@@ -3,15 +3,15 @@
 You are running inside CI for the `unity-mcp` repo. Use only the tools allowed by the workflow. Work autonomously; do not prompt the user. Do NOT spawn subagents.
 
 **Print this once, verbatim, early in the run:**
-AllowedTools: Write,mcp__unity__manage_editor,mcp__unity__list_resources,mcp__unity__read_resource,mcp__unity__apply_text_edits,mcp__unity__script_apply_edits,mcp__unity__validate_script,mcp__unity__find_in_file,mcp__unity__read_console,mcp__unity__get_sha
+AllowedTools: Write,mcp__UnityMCP__apply_text_edits,mcp__UnityMCP__script_apply_edits,mcp__UnityMCP__validate_script,mcp__UnityMCP__find_in_file,mcp__UnityMCP__read_console,mcp__UnityMCP__get_sha
 
 ---
 
 ## Mission
 1) Pick target file (prefer):
    - `unity://path/Assets/Scripts/LongUnityScriptClaudeTest.cs`
 2) Execute NL tests NL-0..NL-4 in order using minimal, precise edits that build on each other.
-3) Validate each edit with `mcp__unity__validate_script(level:"standard")`.
+3) Validate each edit with `mcp__UnityMCP__validate_script(level:"standard")`.
 4) **Report**: write one `<testcase>` XML fragment per test to `reports/<TESTID>_results.xml`. Do **not** read or edit `$JUNIT_OUT`.
 
 **CRITICAL XML FORMAT REQUIREMENTS:**
@@ -50,7 +50,7 @@ CI provides:
 ## Transcript Minimization Rules
 - Do not restate tool JSON; summarize in ≤ 2 short lines.
 - Never paste full file contents. For matches, include only the matched line and ±1 line.
-- Prefer `mcp__unity__find_in_file` for targeting; avoid `mcp__unity__read_resource` unless strictly necessary. If needed, limit to `head_bytes ≤ 256` or `tail_lines ≤ 10`.
+- Prefer `mcp__UnityMCP__find_in_file` for targeting to minimize transcript size.
 - Per‑test `system-out` ≤ 400 chars: brief status only (no SHA).
 - Console evidence: fetch the last 10 lines with `include_stacktrace:false` and include ≤ 3 lines in the fragment.
 - Avoid quoting multi‑line diffs; reference markers instead.
@@ -59,17 +59,17 @@ CI provides:
 ---
 
 ## Tool Mapping
-- **Anchors/regex/structured**: `mcp__unity__script_apply_edits`
+- **Anchors/regex/structured**: `mcp__UnityMCP__script_apply_edits`
   - Allowed ops: `anchor_insert`, `replace_method`, `insert_method`, `delete_method`, `regex_replace`
   - For `anchor_insert`, always set `"position": "before"` or `"after"`.
-- **Precise ranges / atomic batch**: `mcp__unity__apply_text_edits` (non‑overlapping ranges)
+- **Precise ranges / atomic batch**: `mcp__UnityMCP__apply_text_edits` (non‑overlapping ranges)
 STRICT OP GUARDRAILS
 - Do not use `anchor_replace`. Structured edits must be one of: `anchor_insert`, `replace_method`, `insert_method`, `delete_method`, `regex_replace`.
-- For multi‑spot textual tweaks in one operation, compute non‑overlapping ranges with `mcp__unity__find_in_file` and use `mcp__unity__apply_text_edits`.
+- For multi‑spot textual tweaks in one operation, compute non‑overlapping ranges with `mcp__UnityMCP__find_in_file` and use `mcp__UnityMCP__apply_text_edits`.
 
-- **Hash-only**: `mcp__unity__get_sha` — returns `{sha256,lengthBytes,lastModifiedUtc}` without file body
-- **Validation**: `mcp__unity__validate_script(level:"standard")`
-- **Dynamic targeting**: Use `mcp__unity__find_in_file` to locate current positions of methods/markers
+- **Hash-only**: `mcp__UnityMCP__get_sha` — returns `{sha256,lengthBytes,lastModifiedUtc}` without file body
+- **Validation**: `mcp__UnityMCP__validate_script(level:"standard")`
+- **Dynamic targeting**: Use `mcp__UnityMCP__find_in_file` to locate current positions of methods/markers
 
 ---
 
@@ -83,7 +83,7 @@ STRICT OP GUARDRAILS
 5. **Composability**: Tests demonstrate how operations work together in real workflows
 
 **State Tracking:**
-- Track file SHA after each test (`mcp__unity__get_sha`) for potential preconditions in later passes. Do not include SHA values in report fragments.
+- Track file SHA after each test (`mcp__UnityMCP__get_sha`) for potential preconditions in later passes. Do not include SHA values in report fragments.
 - Use content signatures (method names, comment markers) to verify expected state
 - Validate structural integrity after each major change
 

.claude/prompts/nl-unity-suite-t.md

@@ -2,15 +2,15 @@
 You are running inside CI for the `unity-mcp` repo. Use only the tools allowed by the workflow. Work autonomously; do not prompt the user. Do NOT spawn subagents.
 
 **Print this once, verbatim, early in the run:**
-AllowedTools: Write,mcp__unity__manage_editor,mcp__unity__list_resources,mcp__unity__read_resource,mcp__unity__apply_text_edits,mcp__unity__script_apply_edits,mcp__unity__validate_script,mcp__unity__find_in_file,mcp__unity__read_console,mcp__unity__get_sha
+AllowedTools: Write,mcp__UnityMCP__manage_editor,mcp__UnityMCP__list_resources,mcp__UnityMCP__read_resource,mcp__UnityMCP__apply_text_edits,mcp__UnityMCP__script_apply_edits,mcp__UnityMCP__validate_script,mcp__UnityMCP__find_in_file,mcp__UnityMCP__read_console,mcp__UnityMCP__get_sha
 
 ---
 
 ## Mission
 1) Pick target file (prefer):
    - `unity://path/Assets/Scripts/LongUnityScriptClaudeTest.cs`
 2) Execute T tests T-A..T-J in order using minimal, precise edits that build on the NL pass state.
-3) Validate each edit with `mcp__unity__validate_script(level:"standard")`.
+3) Validate each edit with `mcp__UnityMCP__validate_script(level:"standard")`.
 4) **Report**: write one `<testcase>` XML fragment per test to `reports/<TESTID>_results.xml`. Do **not** read or edit `$JUNIT_OUT`.
 
 **CRITICAL XML FORMAT REQUIREMENTS:**
@@ -49,7 +49,7 @@ CI provides:
 ## Transcript Minimization Rules
 - Do not restate tool JSON; summarize in ≤ 2 short lines.
 - Never paste full file contents. For matches, include only the matched line and ±1 line.
-- Prefer `mcp__unity__find_in_file` for targeting; avoid `mcp__unity__read_resource` unless strictly necessary. If needed, limit to `head_bytes ≤ 256` or `tail_lines ≤ 10`.
+- Prefer `mcp__UnityMCP__find_in_file` for targeting; avoid `mcp__UnityMCP__read_resource` unless strictly necessary. If needed, limit to `head_bytes ≤ 256` or `tail_lines ≤ 10`.
 - Per‑test `system-out` ≤ 400 chars: brief status only (no SHA).
 - Console evidence: fetch the last 10 lines with `include_stacktrace:false` and include ≤ 3 lines in the fragment.
 - Avoid quoting multi‑line diffs; reference markers instead.
@@ -59,17 +59,17 @@ CI provides:
 ---
 
 ## Tool Mapping
-- **Anchors/regex/structured**: `mcp__unity__script_apply_edits`
+- **Anchors/regex/structured**: `mcp__UnityMCP__script_apply_edits`
   - Allowed ops: `anchor_insert`, `replace_method`, `insert_method`, `delete_method`, `regex_replace`
   - For `anchor_insert`, always set `"position": "before"` or `"after"`.
-- **Precise ranges / atomic batch**: `mcp__unity__apply_text_edits` (non‑overlapping ranges)
+- **Precise ranges / atomic batch**: `mcp__UnityMCP__apply_text_edits` (non‑overlapping ranges)
 STRICT OP GUARDRAILS
 - Do not use `anchor_replace`. Structured edits must be one of: `anchor_insert`, `replace_method`, `insert_method`, `delete_method`, `regex_replace`.
-- For multi‑spot textual tweaks in one operation, compute non‑overlapping ranges with `mcp__unity__find_in_file` and use `mcp__unity__apply_text_edits`.
+- For multi‑spot textual tweaks in one operation, compute non‑overlapping ranges with `mcp__UnityMCP__find_in_file` and use `mcp__UnityMCP__apply_text_edits`.
 
-- **Hash-only**: `mcp__unity__get_sha` — returns `{sha256,lengthBytes,lastModifiedUtc}` without file body
-- **Validation**: `mcp__unity__validate_script(level:"standard")`
-- **Dynamic targeting**: Use `mcp__unity__find_in_file` to locate current positions of methods/markers
+- **Hash-only**: `mcp__UnityMCP__get_sha` — returns `{sha256,lengthBytes,lastModifiedUtc}` without file body
+- **Validation**: `mcp__UnityMCP__validate_script(level:"standard")`
+- **Dynamic targeting**: Use `mcp__UnityMCP__find_in_file` to locate current positions of methods/markers
 
 ---
 
@@ -83,7 +83,7 @@ STRICT OP GUARDRAILS
 5. **Composability**: Tests demonstrate how operations work together in real workflows
 
 **State Tracking:**
-- Track file SHA after each test (`mcp__unity__get_sha`) and use it as a precondition
+- Track file SHA after each test (`mcp__UnityMCP__get_sha`) and use it as a precondition
   for `apply_text_edits` in T‑F/T‑G/T‑I to exercise `stale_file` semantics. Do not include SHA values in report fragments.
 - Use content signatures (method names, comment markers) to verify expected state
 - Validate structural integrity after each major change
@@ -100,14 +100,14 @@ STRICT OP GUARDRAILS
 - **Expected final state**: Return to State C (helper removed, other changes intact)
 
 ### Late-Test Editing Rule
-- When modifying a method body, use `mcp__unity__script_apply_edits`. If the method is expression-bodied (`=>`), convert it to a block or replace the whole method definition. After the edit, run `mcp__unity__validate_script` and rollback on error. Use `//` comments in inserted code.
+- When modifying a method body, use `mcp__UnityMCP__script_apply_edits`. If the method is expression-bodied (`=>`), convert it to a block or replace the whole method definition. After the edit, run `mcp__UnityMCP__validate_script` and rollback on error. Use `//` comments in inserted code.
 
 ### T-B. Method Body Interior Edit (Additive State D)
 **Goal**: Edit method interior without affecting structure, on modified file
 **Actions**:
 - Use `find_in_file` to locate current `HasTarget()` method (modified in NL-1)
 - Edit method body interior: change return statement to `return true; /* test modification */`
-- Validate with `mcp__unity__validate_script(level:"standard")` for consistency
+- Validate with `mcp__UnityMCP__validate_script(level:"standard")` for consistency
 - Verify edit succeeded and file remains balanced
 - **Expected final state**: State C + modified HasTarget() body
 
@@ -124,7 +124,7 @@ STRICT OP GUARDRAILS
 **Actions**:
 - Use smart anchor matching to find current class-ending brace (after NL-3 tail comments)
 - Insert permanent helper before class brace: `private void TestHelper() { /* placeholder */ }`
-- Validate with `mcp__unity__validate_script(level:"standard")`
+- Validate with `mcp__UnityMCP__validate_script(level:"standard")`
 - **IMMEDIATELY** write clean XML fragment to `reports/T-D_results.xml` (no extra text). The `<testcase name>` must start with `T-D`. Include brief evidence in `system-out`.
 - **Expected final state**: State E + TestHelper() method before class end
 
@@ -178,12 +178,12 @@ STRICT OP GUARDRAILS
 ### T-J. Idempotency on Modified File (Additive State I)
 **Goal**: Verify operations behave predictably when repeated
 **Actions**:
-- **Insert (structured)**: `mcp__unity__script_apply_edits` with:
+- **Insert (structured)**: `mcp__UnityMCP__script_apply_edits` with:
   `{"op":"anchor_insert","anchor":"// Tail test C","position":"after","text":"\n    // idempotency test marker"}`
 - **Insert again** (same op) → expect `no_op: true`.
 - **Remove (structured)**: `{"op":"regex_replace","pattern":"(?m)^\\s*// idempotency test marker\\r?\\n?","text":""}`
 - **Remove again** (same `regex_replace`) → expect `no_op: true`.
-- `mcp__unity__validate_script(level:"standard")`
+- `mcp__UnityMCP__validate_script(level:"standard")`
 - Perform a final console scan for errors/exceptions (errors only, up to 3); include "no errors" if none
 - **IMMEDIATELY** write clean XML fragment to `reports/T-J_results.xml` with evidence of both `no_op: true` outcomes and the console result. The `<testcase name>` must start with `T-J`.
 - **Expected final state**: State H + verified idempotent behavior