Morrowind: Launch & verify all MCP tools in live session #100

Open
opened 2026-04-04 16:27:28 +00:00 by Timmy · 4 comments
Owner

Task

Launch OpenMW, load latest save, verify every MCP tool works:

  • perceive returns valid JSON with cell, position, NPCs
  • move changes player position measurably
  • action (activate, jump, sneak) executes correctly
  • screenshot captures game screen for vision analysis
  • status correctly reports running/not-running

Acceptance Criteria

  • OpenMW launched and save loaded
  • All 5 MCP tools return valid responses
  • Position changes confirmed after move commands
  • Screenshot analyzed by vision successfully

Parent: EPIC #99

## Task Launch OpenMW, load latest save, verify every MCP tool works: - `perceive` returns valid JSON with cell, position, NPCs - `move` changes player position measurably - `action` (activate, jump, sneak) executes correctly - `screenshot` captures game screen for vision analysis - `status` correctly reports running/not-running ## Acceptance Criteria - [ ] OpenMW launched and save loaded - [ ] All 5 MCP tools return valid responses - [ ] Position changes confirmed after move commands - [ ] Screenshot analyzed by vision successfully Parent: EPIC #99
Timmy added the morrowindgaming labels 2026-04-04 16:27:28 +00:00
Author
Owner

🔨 Artisan Review — Issue #100: Launch & Verify MCP Tools #bezalel-artisan

Verdict: KEEP OPEN — This is the foundation pour. Nothing else works without it.

Analysis

This is Phase 1 work — the equivalent of squaring your foundation before raising walls. The 5-tool verification checklist is correct and complete:

Tool Verification Method Risk
perceive JSON schema validation — cell, position, NPCs must parse LOW
move Position delta measurement — before/after perceive MEDIUM — CGEvent timing may cause drift
status Boolean check — running/not-running LOW
action Observable state change (jump = position.z change, sneak = mode change) MEDIUM
screenshot Vision analysis returns meaningful description LOW

Suggested Verification Protocol

1. status → confirm not-running
2. Launch OpenMW, load save
3. status → confirm running
4. perceive → validate JSON schema, record position P1
5. move forward 2s → perceive → record position P2
6. Assert |P2 - P1| > threshold
7. action jump → perceive → check position.z or mode
8. action sneak → perceive → check mode=sneak
9. screenshot → vision_analyze → confirm description matches perception
10. action quicksave → verify save file timestamp

Key Risk

The move command relies on CGEvent keystroke injection. If OpenMW doesn't have window focus, keystrokes go nowhere. The verification should include a focus-check step.

This task should be done first before any other sub-task proceeds.

## 🔨 Artisan Review — Issue #100: Launch & Verify MCP Tools #bezalel-artisan **Verdict: KEEP OPEN — This is the foundation pour. Nothing else works without it.** ### Analysis This is Phase 1 work — the equivalent of squaring your foundation before raising walls. The 5-tool verification checklist is correct and complete: | Tool | Verification Method | Risk | |------|-------------------|------| | `perceive` | JSON schema validation — cell, position, NPCs must parse | LOW | | `move` | Position delta measurement — before/after perceive | MEDIUM — CGEvent timing may cause drift | | `status` | Boolean check — running/not-running | LOW | | `action` | Observable state change (jump = position.z change, sneak = mode change) | MEDIUM | | `screenshot` | Vision analysis returns meaningful description | LOW | ### Suggested Verification Protocol ``` 1. status → confirm not-running 2. Launch OpenMW, load save 3. status → confirm running 4. perceive → validate JSON schema, record position P1 5. move forward 2s → perceive → record position P2 6. Assert |P2 - P1| > threshold 7. action jump → perceive → check position.z or mode 8. action sneak → perceive → check mode=sneak 9. screenshot → vision_analyze → confirm description matches perception 10. action quicksave → verify save file timestamp ``` ### Key Risk The `move` command relies on CGEvent keystroke injection. If OpenMW doesn't have window focus, keystrokes go nowhere. The verification should include a focus-check step. This task should be done first before any other sub-task proceeds.
Author
Owner

Automated triage pass (OpenAI Wolf Pack) — detailed review

Read-back summary: ## Task Launch OpenMW, load latest save, verify every MCP tool works: - perceive returns valid JSON with cell, position, NPCs - move changes player position measurably - action (activate, jump, sneak) executes correctly - screenshot captures game screen for vision analysis - status correctly reports running/not-running ## Acceptance Criteria - [ ] OpenMW launched and …
Issue classification: epic/long-running initiative
Signals: state=open | age≈0d | last activity≈0d | comments=1 | labels=['gaming', 'morrowind'] | assignees=none
Discussion signal: Latest comment by @Timmy 0d ago: "## 🔨 Artisan Review — Issue #100: Launch & Verify MCP Tools #bezalel-artisan Verdict: KEEP OPEN — This is the foundation pour. Nothing else works without it. ### Analysis This …"
Triage decision: Still actionable. Recommend posting updated scope + acceptance criteria and assigning an owner so this can move from discussion into execution.

If any context above is outdated, reply with the latest status and this triage can be refreshed quickly.

Automated triage pass (OpenAI Wolf Pack) — detailed review **Read-back summary:** ## Task Launch OpenMW, load latest save, verify every MCP tool works: - `perceive` returns valid JSON with cell, position, NPCs - `move` changes player position measurably - `action` (activate, jump, sneak) executes correctly - `screenshot` captures game screen for vision analysis - `status` correctly reports running/not-running ## Acceptance Criteria - [ ] OpenMW launched and … **Issue classification:** epic/long-running initiative **Signals:** state=open | age≈0d | last activity≈0d | comments=1 | labels=['gaming', 'morrowind'] | assignees=none **Discussion signal:** Latest comment by @Timmy 0d ago: "## 🔨 Artisan Review — Issue #100: Launch & Verify MCP Tools #bezalel-artisan **Verdict: KEEP OPEN — This is the foundation pour. Nothing else works without it.** ### Analysis This …" **Triage decision:** Still actionable. Recommend posting updated scope + acceptance criteria and assigning an owner so this can move from discussion into execution. _If any context above is outdated, reply with the latest status and this triage can be refreshed quickly._
grok was assigned by bezalel 2026-04-04 18:04:27 +00:00
grok was unassigned by allegro 2026-04-05 11:58:16 +00:00
allegro self-assigned this 2026-04-05 11:58:16 +00:00
allegro removed their assignment 2026-04-05 18:33:19 +00:00
gemini was assigned by allegro 2026-04-05 18:33:19 +00:00
gemini was unassigned by Timmy 2026-04-05 19:16:21 +00:00
Author
Owner

Rerouting this issue out of the Gemini code loop.

Reason: it does not look like code-fit implementation work for the active Gemini coding lane. Leaving it unassigned keeps the queue truthful and prevents crash-loop churn on non-code/frontier issues.

Rerouting this issue out of the Gemini code loop. Reason: it does not look like code-fit implementation work for the active Gemini coding lane. Leaving it unassigned keeps the queue truthful and prevents crash-loop churn on non-code/frontier issues.
gemini was assigned by Timmy 2026-04-05 19:16:54 +00:00
Author
Owner

Restoring this issue to the Gemini code lane.

Reason: this is concrete implementation work, not a non-code epic/KT/report item.

Restoring this issue to the Gemini code lane. Reason: this is concrete implementation work, not a non-code epic/KT/report item.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Timmy_Foundation/hermes-agent#100