feat: fix default and free models

[neubig]

HUMAN:

I tested the onboarding LLM settings and verified the OpenAI / GPT-5.6 Sol default and Free model badge behavior.

AGENT:

Why

The OpenHands source default should use the OpenAI provider with GPT-5.6 Sol, matching the requested product decision. DeepSeek V4 Flash remains available as the sole free OpenHands-routed model.

Summary

• Make openai/gpt-5.6-sol the Canvas and onboarding default.
• Keep only openhands/deepseek-v4-flash in the frontend free-model labels.
• Update mocks, translations, specs, and affected tests.

Issue Number

Fixes #16914

How to Test

• npm run make-i18n
• npx vitest run __tests__/api/settings-service.test.ts __tests__/components/settings/llm-profiles/llm-settings-local-view.test.tsx __tests__/utils/format-model-name.test.ts
• npm run typecheck

Video/Screenshots

Verification screenshots

• Clean default LLM settings screenshot: OpenAI / gpt-5.6-sol selected on first opening.
• Clean Free-model selector screenshot: only deepseek-v4-flash is marked Free; glm-5.2 is not.

Validation

• 66 targeted tests passed.
• TypeScript typecheck passed.
• git diff --check passed.

The SaaS pricing PR remains OpenHands/saas-deploy#801. The enterprise PR remains OpenHands/enterprise#253 and intentionally keeps its DeepSeek migration.

This pull request was created by an AI agent (OpenHands) on behalf of the user.

---

🐳 Docker images for this PR

• GHCR package: https://github.com/OpenHands/OpenHands/pkgs/container/agent-canvas

Component	Value
Image	ghcr.io/openhands/agent-canvas
Architectures	amd64, arm64
Agent Server	ghcr.io/openhands/agent-server:1.42.1-python
Automation	openhands-automation==1.8.0
Commit	76d5404bfcdff804abf239d0b523d3f78942747e

Pull (multi-arch manifest)

# Multi-arch manifest — Docker automatically pulls the correct architecture
docker pull ghcr.io/openhands/agent-canvas:sha-76d5404

Run

docker run -it --rm \
  -p 8000:8000 \
  ghcr.io/openhands/agent-canvas:sha-76d5404

All tags pushed for this build

ghcr.io/openhands/agent-canvas:sha-76d5404-amd64
ghcr.io/openhands/agent-canvas:change-deepseek-default-amd64
ghcr.io/openhands/agent-canvas:pr-16922-amd64
ghcr.io/openhands/agent-canvas:sha-76d5404-arm64
ghcr.io/openhands/agent-canvas:change-deepseek-default-arm64
ghcr.io/openhands/agent-canvas:pr-16922-arm64
ghcr.io/openhands/agent-canvas:sha-76d5404
ghcr.io/openhands/agent-canvas:change-deepseek-default
ghcr.io/openhands/agent-canvas:pr-16922

About Multi-Architecture Support

• Each tag (e.g., sha-76d5404) is a multi-arch manifest supporting both amd64 and arm64
• Docker automatically pulls the correct architecture for your platform
• Individual architecture tags (e.g., sha-76d5404-amd64) are also available if needed

[all-hands-bot]

👋 This PR needs a couple of things fixed before OpenHands can review it:

• the PR description's HUMAN: section needs at least 20 characters describing what you tested, not just the template placeholder

Push an update once this is addressed and this check re-runs automatically.

This is an automated check - no AI was used to generate this comment.

[github-actions]

✅ Mock-LLM Docker E2E Test Results

66/66 passed

Commit: 76d5404b · Workflow run · Test artifacts

Details

Status	Test	Duration
✅	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 1: setup LLM profile and register automation trajectory	6.6s
✅	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 2: create automation and dispatch run via the UI	36.7s
✅	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 3: verify automation and run on the automations page	6.0s
✅	automations/mock-llm-preset-automation.spec.ts › preset automation → slash command conversation › automation card sends the correct slash command to a conversation	15.8s
✅	automations/mock-llm-preset-automation.spec.ts › preset automation → slash command conversation › direct slash command from home page triggers skill activation	12.6s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: fresh install with runtime-injected key › reaches the onboarding modal without pre-seeded localStorage	1.4s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: non-public key rotation › recovers when localStorage has a stale session API key	5.5s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › shows first-run onboarding before the auth screen when no key is configured	1.4s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › rejects an incorrect key with an inline error	1.5s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › allows access after pasting the correct key	1.7s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › skips auth screen for returning user with valid stored key	1.3s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › re-prompts when the server rotates its key (stale localStorage)	1.6s
✅	backends/mock-llm-cross-connect.spec.ts › cross-connect: frontend-only → backend-only › frontend-only connects to a separate backend-only instance	24.2s
✅	backends/mock-llm-cross-connect.spec.ts › cross-connect: frontend-only → multiple backends › connects to two separate backends and switches between them	23.0s
✅	backends/mock-llm-cross-connect.spec.ts › cross-connect: sidebar links pin their backend › cmd-clicking a sidebar conversation opens it on the owning backend	31.6s
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: --frontend-only › serves the frontend but returns 503 for backend routes	7.4s
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: --backend-only › serves backend APIs but returns 503 for the frontend root	16.1s
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: port conflict › fails with a clear error when the ingress port is occupied	104ms
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: port conflict › starts successfully on a free port after a conflict	6.0s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 1: create an LLM profile pointing at the mock LLM server	6.3s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 2: activate the mock-llm profile and verify settings API	6.3s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 3: run a conversation with the mock LLM	6.5s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 4: resume conversation from sidebar after navigating away	6.0s
✅	conversations/mock-llm-image-upload.spec.ts › mock-LLM image upload › attaching an image embeds it as base64 in the LLM completion call	12.7s
✅	files/mock-llm-files-and-git.spec.ts › files tab, conversation overview git, and browser tab › step 1: ensure mock LLM profile is configured	6.4s
✅	files/mock-llm-files-and-git.spec.ts › files tab, conversation overview git, and browser tab › step 2: start conversation and attach workspace metadata	11.7s
✅	files/mock-llm-files-and-git.spec.ts › files tab, conversation overview git, and browser tab › step 3: conversation overview shows workspace and git identity	26.2s
✅	files/mock-llm-files-and-git.spec.ts › files tab, conversation overview git, and browser tab › step 4: commits tab opens for attached workspace	5.8s
✅	files/mock-llm-files-and-git.spec.ts › files tab, conversation overview git, and browser tab › step 5: browser tab shows empty state	6.4s
✅	files/mock-llm-files-and-git.spec.ts › files tab, conversation overview git, and browser tab › step 6: files tab defaults to file-tree view without attached workspace	7.0s
✅	home/mock-llm-folder-workspace.spec.ts › mock-LLM folder browser → workspace → conversation › step 1: browse to a folder, add it as a workspace, and launch a conversation with the correct working_dir	7.2s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 1: GitHub card is visible on the MCP marketplace page	5.6s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 2: clicking GitHub add control opens the install modal with correct fields	5.8s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 3: full install flow — fill PAT, submit, verify installed	12.1s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 4: installed GitHub server can be deleted	5.9s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › regression: sibling create, edit, and delete preserve GitHub credentials with one MCP request each	12.9s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › install: invalid Slack credentials are blocked with a credential-check error	5.8s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › install: a valid token missing only a scope still installs (missing_scope is not a credential failure)	5.8s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › install: an older agent server that omits tool_result still installs (compat)	5.8s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › edit: Test Connection verifies the stored credentials and surfaces a credential failure	5.8s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › edit: Test Connection reports success for valid stored credentials	5.7s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › custom (non-catalog) server: Test Connection attaches no verification probe	5.8s
✅	onboarding/mock-llm-onboarding-happy-path.spec.ts › onboarding happy path › completes the full onboarding flow and launches a conversation	4.3s
✅	onboarding/mock-llm-onboarding-regressions.spec.ts › onboarding recent regressions › keeps the modal open on backdrop click and Escape	1.6s
✅	onboarding/mock-llm-onboarding-regressions.spec.ts › onboarding recent regressions › defaults the LLM setup step to OpenAI GPT-5.6 Sol	1.6s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › scopes standalone styles to the agent-server-ui shell	1.5s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › renders critic results on agent messages and finish actions	1.5s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › loads older events when scrolling up	2.0s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › selected workspace persists after navigating away and returning	2.5s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › cleared sessionStorage yields empty workspace selection	1.3s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 1: configure ACP agent via Settings → Agent UI	13.3s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 2: reload and verify ACP settings are persisted in UI	5.8s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 3: start ACP conversation and verify agent reply	8.8s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 4: resume ACP conversation from sidebar after navigating away	5.9s
✅	settings/mock-llm-acp-auth-banner.spec.ts › mock-LLM ACP credentials-configured banner (#1244) › Claude credential in the store surfaces a 'configured' banner, never 'signed in'	6.9s
✅	settings/mock-llm-cloud-providers-pagination.spec.ts › cloud LLM provider-picker pagination › surfaces providers past page 1 (e.g. xai) in the picker on a cloud backend	6.3s
✅	settings/mock-llm-cloud-providers-pagination.spec.ts › cloud LLM provider-picker pagination › does not regress the local path: 150+ providers render in the picker	5.8s
✅	settings/mock-llm-model-switch.spec.ts › mock-LLM /model slash command › step 1: configure LLM, create switch-target profile, register trajectory	7.1s
✅	settings/mock-llm-model-switch.spec.ts › mock-LLM /model slash command › step 2: start conversation, switch profile via /model, verify switch	6.8s
✅	settings/mock-llm-profile-management.spec.ts › active profile deletion + reconciliation › active profile is deletable and reconciliation activates another profile	8.1s
✅	settings/mock-llm-profile-management.spec.ts › same-model profile identity › chat header shows the correct profile when two profiles share the same model	14.5s
✅	settings/mock-llm-profile-management.spec.ts › OpenHands provider hidden base_url preservation › re-saving an OpenHands profile from Basic view preserves hidden base_url	7.4s
✅	settings/mock-llm-provider-connection-selector.spec.ts › provider connection selector › selects a supported provider in Add provider	8.2s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › project skill in workspace/.agents/skills/ triggers on matching keyword	12.9s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › user skill in ~/.openhands/skills/ triggers on matching keyword	7.7s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › deleting a user skill removes it from subsequent conversations	7.6s

_{Posted by the Mock-LLM E2E workflow · results are deterministic (scripted LLM responses)}

[github-actions]

❌ Mock-LLM E2E Tests

63/66 passed · 1 failed · 2 skipped

Commit: 76d5404b · Workflow run · Test artifacts

Details

Status	Test	Duration
✅	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 1: setup LLM profile and register automation trajectory	6.6s
❌	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 2: create automation and dispatch run via the UI	39.3s
⏭️	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 3: verify automation and run on the automations page	0ms
✅	automations/mock-llm-preset-automation.spec.ts › preset automation → slash command conversation › automation card sends the correct slash command to a conversation	15.9s
✅	automations/mock-llm-preset-automation.spec.ts › preset automation → slash command conversation › direct slash command from home page triggers skill activation	13.1s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: fresh install with runtime-injected key › reaches the onboarding modal without pre-seeded localStorage	1.5s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: non-public key rotation › recovers when localStorage has a stale session API key	5.5s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › shows first-run onboarding before the auth screen when no key is configured	1.4s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › rejects an incorrect key with an inline error	1.6s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › allows access after pasting the correct key	1.5s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › skips auth screen for returning user with valid stored key	1.0s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › re-prompts when the server rotates its key (stale localStorage)	1.3s
✅	backends/mock-llm-cross-connect.spec.ts › cross-connect: frontend-only → backend-only › frontend-only connects to a separate backend-only instance	17.1s
✅	backends/mock-llm-cross-connect.spec.ts › cross-connect: frontend-only → multiple backends › connects to two separate backends and switches between them	21.6s
✅	backends/mock-llm-cross-connect.spec.ts › cross-connect: sidebar links pin their backend › cmd-clicking a sidebar conversation opens it on the owning backend	32.0s
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: --frontend-only › serves the frontend but returns 503 for backend routes	7.4s
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: --backend-only › serves backend APIs but returns 503 for the frontend root	15.1s
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: port conflict › fails with a clear error when the ingress port is occupied	102ms
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: port conflict › starts successfully on a free port after a conflict	6.0s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 1: create an LLM profile pointing at the mock LLM server	6.3s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 2: activate the mock-llm profile and verify settings API	6.4s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 3: run a conversation with the mock LLM	6.8s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 4: resume conversation from sidebar after navigating away	5.9s
✅	conversations/mock-llm-image-upload.spec.ts › mock-LLM image upload › attaching an image embeds it as base64 in the LLM completion call	13.1s
✅	files/mock-llm-files-and-git.spec.ts › files tab, conversation overview git, and browser tab › step 1: ensure mock LLM profile is configured	6.4s
✅	files/mock-llm-files-and-git.spec.ts › files tab, conversation overview git, and browser tab › step 2: start conversation and attach workspace metadata	11.9s
✅	files/mock-llm-files-and-git.spec.ts › files tab, conversation overview git, and browser tab › step 3: conversation overview shows workspace and git identity	26.2s
✅	files/mock-llm-files-and-git.spec.ts › files tab, conversation overview git, and browser tab › step 4: commits tab opens for attached workspace	5.9s
✅	files/mock-llm-files-and-git.spec.ts › files tab, conversation overview git, and browser tab › step 5: browser tab shows empty state	6.4s
✅	files/mock-llm-files-and-git.spec.ts › files tab, conversation overview git, and browser tab › step 6: files tab defaults to file-tree view without attached workspace	7.3s
✅	home/mock-llm-folder-workspace.spec.ts › mock-LLM folder browser → workspace → conversation › step 1: browse to a folder, add it as a workspace, and launch a conversation with the correct working_dir	7.7s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 1: GitHub card is visible on the MCP marketplace page	5.6s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 2: clicking GitHub add control opens the install modal with correct fields	5.7s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 3: full install flow — fill PAT, submit, verify installed	12.0s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 4: installed GitHub server can be deleted	5.9s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › regression: sibling create, edit, and delete preserve GitHub credentials with one MCP request each	12.8s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › install: invalid Slack credentials are blocked with a credential-check error	5.9s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › install: a valid token missing only a scope still installs (missing_scope is not a credential failure)	5.9s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › install: an older agent server that omits tool_result still installs (compat)	5.9s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › edit: Test Connection verifies the stored credentials and surfaces a credential failure	5.8s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › edit: Test Connection reports success for valid stored credentials	5.8s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › custom (non-catalog) server: Test Connection attaches no verification probe	5.8s
✅	onboarding/mock-llm-onboarding-happy-path.spec.ts › onboarding happy path › completes the full onboarding flow and launches a conversation	5.1s
✅	onboarding/mock-llm-onboarding-regressions.spec.ts › onboarding recent regressions › keeps the modal open on backdrop click and Escape	1.6s
✅	onboarding/mock-llm-onboarding-regressions.spec.ts › onboarding recent regressions › defaults the LLM setup step to OpenAI GPT-5.6 Sol	1.5s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › scopes standalone styles to the agent-server-ui shell	1.5s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › renders critic results on agent messages and finish actions	1.5s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › loads older events when scrolling up	2.0s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › selected workspace persists after navigating away and returning	2.8s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › cleared sessionStorage yields empty workspace selection	1.3s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 1: configure ACP agent via Settings → Agent UI	13.4s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 2: reload and verify ACP settings are persisted in UI	5.8s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 3: start ACP conversation and verify agent reply	8.8s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 4: resume ACP conversation from sidebar after navigating away	5.9s
✅	settings/mock-llm-acp-auth-banner.spec.ts › mock-LLM ACP credentials-configured banner (#1244) › Claude credential in the store surfaces a 'configured' banner, never 'signed in'	6.8s
✅	settings/mock-llm-cloud-providers-pagination.spec.ts › cloud LLM provider-picker pagination › surfaces providers past page 1 (e.g. xai) in the picker on a cloud backend	6.2s
✅	settings/mock-llm-cloud-providers-pagination.spec.ts › cloud LLM provider-picker pagination › does not regress the local path: 150+ providers render in the picker	5.9s
✅	settings/mock-llm-model-switch.spec.ts › mock-LLM /model slash command › step 1: configure LLM, create switch-target profile, register trajectory	7.1s
✅	settings/mock-llm-model-switch.spec.ts › mock-LLM /model slash command › step 2: start conversation, switch profile via /model, verify switch	7.1s
✅	settings/mock-llm-profile-management.spec.ts › active profile deletion + reconciliation › active profile is deletable and reconciliation activates another profile	8.1s
✅	settings/mock-llm-profile-management.spec.ts › same-model profile identity › chat header shows the correct profile when two profiles share the same model	14.7s
✅	settings/mock-llm-profile-management.spec.ts › OpenHands provider hidden base_url preservation › re-saving an OpenHands profile from Basic view preserves hidden base_url	7.6s
✅	settings/mock-llm-provider-connection-selector.spec.ts › provider connection selector › selects a supported provider in Add provider	8.2s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › project skill in workspace/.agents/skills/ triggers on matching keyword	13.2s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › user skill in ~/.openhands/skills/ triggers on matching keyword	7.8s
⏭️	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › deleting a user skill removes it from subsequent conversations	0ms

🔍 Failure details (1)

❌ automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 2: create automation and dispatch run via the UI

Error: Created automation ID was not reported after 30000ms

_{Posted by the Mock-LLM E2E workflow · results are deterministic (scripted LLM responses)}

[all-hands-bot]

🚦 CI is currently failing on this PR's latest commit.

Please fix the failing checks before OpenHands reviews it - this is re-checked automatically once you push a new commit. (A maintainer can also request @all-hands-bot as a reviewer to have it reviewed regardless of CI status.)

This is an automated check - no AI was used to generate this comment.

[juanmichelini]

@OpenHands please create an openhands/saas-deploy feature branch for this

[openhands-ai]

I'm on it! juanmichelini can track my progress at all-hands.dev

[juanmichelini]

@juanmichelini Done — created the OpenHands/saas-deploy feature branch add-gpt-5.6-sol and opened draft PR OpenHands/saas-deploy#813 for it.

It registers the gpt-5.6-sol → openai/gpt-5.6-sol LiteLLM route (via OPENAI_API_KEY) across development, staging, and production so the SaaS can serve the new default. The pricing side (DeepSeek V4 Flash as the sole free route) remains in OpenHands/saas-deploy#801.

One dev-catalog note surfaced in the PR body: development/values.yaml lacks gpt-5.3-codex/gpt-5.4/gpt-5.6, so gpt-5.6-sol was inserted after gpt-5.5 there.

This comment was created by an AI agent (OpenHands) on behalf of the user.

[openhands-ai]

Handled the PR comment. juanmichelini asked for an openhands/saas-deploy feature branch corresponding to frontend PR #16922 (which makes openai/gpt-5.6-sol the OpenHands default model).

What I did:

1. Explored context: Frontend PR feat: fix default and free models #16922 changes the default model to openai/gpt-5.6-sol and keeps only openhands/deepseek-v4-flash as the free route. The referenced SaaS pricing PR (saas-deploy#801) handles the "DeepSeek-only free" pricing side; what was missing on the SaaS side was a LiteLLM route for the new default model.
2. Cloned OpenHands/saas-deploy and created branch add-gpt-5.6-sol.
3. Added the gpt-5.6-sol → openai/gpt-5.6-sol route (using OPENAI_API_KEY) to all three LiteLLM catalogs:
   • app/litellm/environments/development/values.yaml (noted: dev lacks gpt-5.3-codex/gpt-5.4/gpt-5.6, so the new entry sits after gpt-5.5)
   • app/litellm/environments/staging/values.yaml (next to gpt-5.6)
   • app/litellm/environments/production/values.yaml (next to gpt-5.6)
4. Validated: YAML parses in all three files, new gpt-5.6-sol entry confirmed in each model_list, git diff --check clean.
5. Pushed the branch and opened draft PR OpenHands/saas-deploy#813 ("feat(litellm): add gpt-5.6-sol route across environments"), left as a draft since production changes require human review and the user didn't ask to mark it ready.
6. Replied to the comment on OpenHands/OpenHands#16922 with the branch + PR links and the dev-catalog caveat.

No changes were needed in the checked-out frontend workspace; the work lived entirely in the saas-deploy repository.

[neubig]

Updated the onboarding regression assertion to expect gpt-5.6-sol, fixing the deterministic Mock-LLM timeout. This comment was created by an AI agent (OpenHands) on behalf of the user.

[neubig]

needs human approval. Please replace the HUMAN: section placeholder with at least 20 characters describing what you tested; repository policy reserves this section for human contributors.

[neubig]

Fixed the remaining onboarding regression assertions to expect the OpenAI provider, GPT-5.6 Sol, and no OpenHands account helper. Pushed as c4258ce8a. This comment was created by an AI agent (OpenHands) on behalf of the user.

[github-actions]

PR Artifacts Cleaned Up

The .pr/ directory has been removed after approval.

[DevinVinson]

This comment will no longer be correct when the model changes to openai/gpt-5.6-sol since it will not be pre-filled to a free default model.

[neubig]

Fixed in commit a3062b0: corrected the JSDoc to describe the OpenAI GPT-5.6 Sol default and removed the stale OpenHands/free-model wording. This reply was created by an AI agent (OpenHands) on behalf of the user.