Title: **Title:** Support multiple model profiles in settings.json for quick switching via `/model` · Issue #204 · lessweb/deepcode-cli · GitHub
Open Graph Title: **Title:** Support multiple model profiles in settings.json for quick switching via `/model` · Issue #204 · lessweb/deepcode-cli
X Title: **Title:** Support multiple model profiles in settings.json for quick switching via `/model` · Issue #204 · lessweb/deepcode-cli
Description: Problem Currently, settings.json only accepts a single set of model-related configuration: { "model": "deepseek-v4-pro", "thinkingEnabled": true, "reasoningEffort": "max", "temperature": 0 } When I need to switch between different models...
Open Graph Description: Problem Currently, settings.json only accepts a single set of model-related configuration: { "model": "deepseek-v4-pro", "thinkingEnabled": true, "reasoningEffort": "max", "temperature": 0 } When I...
X Description: Problem Currently, settings.json only accepts a single set of model-related configuration: { "model": "deepseek-v4-pro", "thinkingEnabled": true, "reasoningEffort...
Opengraph URL: https://github.com/lessweb/deepcode-cli/issues/204
X: @github
Domain: github.com
{"@context":"https://schema.org","@type":"DiscussionForumPosting","headline":"**Title:** Support multiple model profiles in settings.json for quick switching via `/model`","articleBody":"## Problem\n\nCurrently, `settings.json` only accepts a single set of model-related configuration:\n\n```json\n{\n \"model\": \"deepseek-v4-pro\",\n \"thinkingEnabled\": true,\n \"reasoningEffort\": \"max\",\n \"temperature\": 0\n}\n```\n\nWhen I need to switch between different models (e.g., `deepseek-v4-pro` with max reasoning for complex tasks, `deepseek-v4-flash` without thinking for quick edits), I have to manually adjust each field via `/model` every time — model name, thinking mode, reasoning effort, and temperature. This is repetitive and error-prone.\n\n## Proposed Solution\n\nSupport a `profiles` field in `settings.json` to predefine multiple named configurations:\n\n```json\n{\n \"profiles\": {\n \"pro-max\": {\n \"model\": \"deepseek-v4-pro\",\n \"thinkingEnabled\": true,\n \"reasoningEffort\": \"max\",\n \"temperature\": 0\n },\n \"flash-quick\": {\n \"model\": \"deepseek-v4-flash\",\n \"thinkingEnabled\": false,\n \"temperature\": 0.7\n },\n \"coding-plan\": {\n \"model\": \"ark-code-latest\",\n \"baseUrl\": \"https://ark.cn-beijing.volces.com/api/coding/v3\",\n \"thinkingEnabled\": true\n }\n },\n \"defaultProfile\": \"pro-max\"\n}\n```\n\nThe `/model` command would then list these profiles for one-click switching.\n\n## Use Cases\n\n1. **Heavy reasoning tasks** (architecture design, debugging) → switch to `pro-max`\n2. **Quick edits / boilerplate** → switch to `flash-quick` for speed and cost savings\n3. **Third-party models** (e.g., Coding Plan) → switch to `coding-plan` without re-entering `BASE_URL` and `API_KEY` each time\n\n## Expected Behavior\n\n- `profiles` entries accept: `model`, `baseUrl`, `apiKey`, `thinkingEnabled`, `reasoningEffort`, `temperature`\n- `defaultProfile` (optional) specifies which profile to use at session start\n- `/model` lists all profiles and allows selecting one to apply immediately\n- If `profiles` is not configured, `/model` behaves exactly as it does today\n\n---\n\nThanks for the great tool!","author":{"url":"https://github.com/LoveSilverWolf-999","@type":"Person","name":"LoveSilverWolf-999"},"datePublished":"2026-06-27T01:02:22.000Z","interactionStatistic":{"@type":"InteractionCounter","interactionType":"https://schema.org/CommentAction","userInteractionCount":1},"url":"https://github.com/204/deepcode-cli/issues/204"}
| route-pattern | /_view_fragments/issues/show/:user_id/:repository/:id/issue_layout(.:format) |
| route-controller | voltron_issues_fragments |
| route-action | issue_layout |
| fetch-nonce | v2:f87a1cb9-8196-9ad5-468a-1fa176b74363 |
| current-catalog-service-hash | 81bb79d38c15960b92d99bca9288a9108c7a47b18f2423d0f6438c5b7bcd2114 |
| request-id | E3A0:3D017:10E4E3E:18A229F:6A4E35BC |
| html-safe-nonce | b1fe5e32f54d2e9bcd3f54eaa76d9e6699c0f97910849d8681c28cc0bdb105ed |
| visitor-payload | eyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJFM0EwOjNEMDE3OjEwRTRFM0U6MThBMjI5Rjo2QTRFMzVCQyIsInZpc2l0b3JfaWQiOiIxMjY4NzYxNjc5MjE2MTI5NDY4IiwicmVnaW9uX2VkZ2UiOiJpYWQiLCJyZWdpb25fcmVuZGVyIjoiaWFkIn0= |
| visitor-hmac | 927517f072e51807f9ecf75a770fe2db615b488490a660f2f3d1201f8aec1213 |
| hovercard-subject-tag | issue:4756052813 |
| github-keyboard-shortcuts | repository,issues,copilot |
| google-site-verification | Apib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I |
| octolytics-url | https://collector.github.com/github/collect |
| analytics-location | / |
| fb:app_id | 1401488693436528 |
| apple-itunes-app | app-id=1477376905, app-argument=https://github.com/_view_fragments/issues/show/lessweb/deepcode-cli/204/issue_layout |
| twitter:image | https://opengraph.githubassets.com/6d88539712aba076a39b9295390855fa60bbef5cbcbe97cfd1d88fbe819310b8/lessweb/deepcode-cli/issues/204 |
| twitter:card | summary_large_image |
| og:image | https://opengraph.githubassets.com/6d88539712aba076a39b9295390855fa60bbef5cbcbe97cfd1d88fbe819310b8/lessweb/deepcode-cli/issues/204 |
| og:image:alt | Problem Currently, settings.json only accepts a single set of model-related configuration: { "model": "deepseek-v4-pro", "thinkingEnabled": true, "reasoningEffort": "max", "temperature": 0 } When I... |
| og:image:width | 1200 |
| og:image:height | 600 |
| og:site_name | GitHub |
| og:type | object |
| og:author:username | LoveSilverWolf-999 |
| hostname | github.com |
| expected-hostname | github.com |
| None | 030096ee0db095447bfe77409d33bfac127ca7128299c58deef27c52eaa1b1f0 |
| turbo-cache-control | no-preview |
| go-import | github.com/lessweb/deepcode-cli git https://github.com/lessweb/deepcode-cli.git |
| octolytics-dimension-user_id | 118287711 |
| octolytics-dimension-user_login | lessweb |
| octolytics-dimension-repository_id | 1223512305 |
| octolytics-dimension-repository_nwo | lessweb/deepcode-cli |
| octolytics-dimension-repository_public | true |
| octolytics-dimension-repository_is_fork | false |
| octolytics-dimension-repository_network_root_id | 1223512305 |
| octolytics-dimension-repository_network_root_nwo | lessweb/deepcode-cli |
| turbo-body-classes | logged-out env-production page-responsive |
| disable-turbo | false |
| browser-stats-url | https://api.github.com/_private/browser/stats |
| browser-errors-url | https://api.github.com/_private/browser/errors |
| release | 42a6d378d7587a44c93aca255096cd66b7c8eb2d |
| ui-target | full |
| theme-color | #1e2327 |
| color-scheme | light dark |
Links:
Viewport: width=device-width