Add custom provider_type for generic OpenAI-compatible endpoints

[anhle128]

Problem

Provider catalog currently hard-codes known vendors (Anthropic, OpenAI, DashScope, Claude CLI, ACP, Codex). Users running self-hosted or niche OpenAI-compatible gateways (vLLM, LM Studio, LiteLLM,
Ollama proxy, OpenRouter, Together, Groq, Fireworks, local inference) cannot register them without either (a) hijacking the openai type and mismatching defaults, or (b) shipping a new provider_type per
vendor. Neither scales.

Goal

Introduce a neutral custom provider_type that treats any endpoint as OpenAI chat-completions compatible, so ops teams can onboard new backends via config/UI without code changes.

Scope

In scope

• Backend: accept provider_type = "custom" in provider store + HTTP validation.
• Routing: resolve custom through the existing OpenAI-compatible adapter (HTTP + SSE).
• Model listing: expose /v1/models passthrough for custom endpoints.
• UI: add "Custom Provider" entry in provider dropdown with i18n (en/vi/zh).
• Tests: unit + integration contract coverage.

Out of scope

• Non-OpenAI wire formats (Cohere, Bedrock native, Vertex native).
• Per-custom-provider feature flags (vision, tool-use capability negotiation) — deferred.
• UI credential templates per vendor.

Acceptance Criteria

• Creating a provider with provider_type=custom, base_url, encrypted api_key persists and appears in list endpoint.
• Chat completion request routed to custom provider returns streamed SSE response identical in shape to openai type.
• Model listing endpoint returns models reported by the custom backend.
• UI dropdown shows "Custom Provider" in en/vi/zh; selecting it saves provider_type=custom.
• go test ./internal/http/... ./internal/store/... + go test -tags integration ./tests/contracts/http_api/... pass.
• cd ui/web && pnpm test passes.

[tienlx91]

There is already an OpenAI-compatible API. I've tried adding my self-hosted Ollama server (it's my PC exposed via a Cloudflare Tunnel), and it works great. Try it.

---

@thieung there is an annoying issue: when I first added the wrong URL (I forgot the /v1 at the end), the provider accepted it successfully. I then opened Advanced settings to update the API key. After saving and reloading the dashboard, I received an infinite loop error and cannot access the dashboard again, response:

{"error":"failed to list providers"}

I have to manual SSH to the GoClaw server and manual remove so that I can access the dashboard again.

---

P/S: I tell claude code to find the root caused, here is the reason:

Root cause: The settings column in llm_providers is scanned into json.RawMessage (which is []byte). The built-in provider created at init has settings stored as SQLite blob → works fine. But when you create/edit a provider through the dashboard UI, the settings JSON gets stored as SQLite text type. Go's database/sql can't scan a string into *json.RawMessage — it only accepts []byte.

Since the error fires on SELECT * FROM llm_providers, one bad row kills the entire list query → dashboard completely unusable.

Repro steps:

Add a new provider via dashboard (e.g. OpenAI-compatible, any settings)
Dashboard immediately stops loading
/v1/providers returns {"error":"failed to list providers"}