voice-to-mermaid: remove vtm-ollama sidecar, default qwen3:8b

[jaewilson07]

Summary

• Remove vestigial vtm-ollama sidecar container + ollama-data volume — api already defaulted to host.docker.internal:11434 (Windows-native Ollama)
• Update config.yaml: default_model was gemma4:31b (did not exist), now qwen3:8b. model_filter updated for models that actually exist.

Context

2026-04-24 reproducibility consolidation. Before this change the backend had:

• vtm-ollama container running but empty (0 models) — unused
• Windows native Ollama serving everything (D:\ollama\models, 16 models from the prior WSL store)
• Conflicting default model advertised (gemma4:31b had phantom manifests, no blobs) causing mermaid page "Generating diagram..." timeouts

Full context: simpleDiscordBot/.agents/plans/2026-04-24_reproducible-infra-consolidation/plan.md

Test plan

• vtm-api container starts cleanly (no references to vtm-ollama)
• /v1/config returns ollama_model: qwen3:8b + updated model_filter
• datacrew.space/projects/mermaid generates a diagram end-to-end

🤖 Generated with Claude Code

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.

[Copilot]

Pull request overview

Removes the unused Ollama sidecar from the Voice-to-Mermaid backend Compose setup and updates the backend configuration to use an available default Ollama model (qwen3:8b) with a corrected model filter.

Changes:

• Deleted the vtm-ollama service and ollama-data volume from docker-compose.yml, switching the API to use Windows-native Ollama via host.docker.internal.
• Added a dedicated local-ai Docker network for the API container.
• Updated config.yaml to set default_model to qwen3:8b and refreshed model_filter to models intended to exist.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 4 comments.

File	Description
voice-to-mermaid/backend/docker-compose.yml	Removes Ollama sidecar, points API at host Ollama, adds local network, adds architecture guidance comments.
voice-to-mermaid/backend/config.yaml	Changes default Ollama model and updates the UI model filter list with additional guidance comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

The comment hardcodes a public VPS IP address. Even in comments, committing infrastructure IPs can increase attack surface and becomes stale quickly; consider referencing a hostname/alias (e.g. "the VPS") or pointing to an internal inventory/runbook instead of embedding the raw IP.

Suggested change

	# ⚠️ DO NOT deploy to the VPS (187.77.216.108) — it has no GPU.
	# ⚠️ DO NOT deploy to the VPS — it has no GPU.

[Copilot]

This comment references infrastructure/local/README.md, but that path does not exist in the repository. Please update the pointer to an existing doc path or remove the reference to avoid broken guidance.

Suggested change

	# ⚠️ See infrastructure/local/README.md for local machine service registry.
	# ⚠️ Local machine only: keep service guidance in repository docs up to date.

[Copilot]

This comment points to .agents/runbooks/troubleshoot-ollama/SKILL.md, but there is no .agents directory in the repo. Please update to an existing runbook location or remove the reference so readers can actually find the architecture rules.

Suggested change

	# See .agents/runbooks/troubleshoot-ollama/SKILL.md for the single-instance
	# architecture rules.
	# Keep this as a single-instance setup: use the existing Windows-native
	# Ollama service and do not reintroduce a Compose-managed Ollama sidecar here.

[Copilot]

The comment uses a user-specific Windows path (C:\Users\jaewi...) and a specific drive letter for OLLAMA_MODELS. Consider making this guidance portable (e.g., %USERPROFILE%\.ollama, or describing how to locate/set OLLAMA_MODELS) so it applies to other developers/machines.

Suggested change

	# Models shown in the UI picker. Must exist in Windows Ollama
	# (C:\Users\jaewi\.ollama is not used — see OLLAMA_MODELS=D:\ollama\models).
	# Models shown in the UI picker. Must exist in Ollama's configured models
	# directory (by default on Windows, under %USERPROFILE%\.ollama; if
	# OLLAMA_MODELS is set, use that location instead).