288 Commits
Author SHA1 Message Date
linshen e5bab3a6a3 fix: restore model tabs and adopt Node 24 2026-09-10 19:31:41 +08:00
linshen bfd1543110 feat: refresh built-in model catalog 2026-09-10 16:42:28 +08:00
linshen e4a281f42d fix: restore model setup access and update dependencies 2026-09-10 15:49:53 +08:00
Iams4kura ef8056cda6 fix(history): preserve record order when restoring backups 2026-09-10 12:26:28 +08:00
arkcia 390377932b fix(template): preserve advanced template imports 2026-08-25 21:45:37 +08:00
linshen bb79051a88 fix: add gpt-image-2 high-resolution sizes 2026-08-13 22:22:58 +08:00
linshen 69a636921e feat: refresh built-in provider models 2026-08-13 22:13:54 +08:00
octo-patch 87668531f5 Add MiniMax regional endpoint metadata 2026-08-12 02:40:49 +08:00
octo-patch 846fe27ed7 Correct MiniMax M2.7 capabilities 2026-08-11 17:45:05 +00:00
kapelame a6a5a17c5a Refresh MiniMax parameters 2026-08-03 14:51:02 +08:00
linshen 0c3679511d fix(test): complete Basic/System image attachment support (#196) 2026-07-18 18:13:41 +08:00
linshen 3126ae4530 feat(test): support image attachments in Basic/System tests (#196) 2026-07-17 23:25:52 +08:00
且炼时光 d7cde6c2fc Merge pull request #308 from chaozai0304/develop
Fixed the OpenAI error when calling large image models: Unknown param…
2026-06-08 14:00:56 +08:00
linshen ecbe788909 fix(evaluation): format provider error details 2026-06-07 10:28:39 +08:00
李超 9ed01ce237 Fixed the OpenAI error when calling large image models: Unknown parameter: 'response_format'. (request id: 202606030925559064897917EvHxr7G) 2026-06-03 10:12:58 +08:00
Octopus 74b06cea72 feat: upgrade MiniMax default model to M3 (#307)
- Add MiniMax-M3 to the model selection list and set as the new default
- Retain MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives
- Remove deprecated MiniMax-M2.5 and MiniMax-M2.5-highspeed from the list
- Update unit tests to match the new model lineup
2026-06-02 09:53:48 +08:00
linshen 9119876b3e feat: add Xiaomi MiMo Token Plan provider 2026-05-27 21:28:37 +08:00
linshen 5d3b7ada92 fix(model): tolerate malformed stored text configs 2026-05-18 21:38:27 +08:00
linshen 74c229a8f5 refactor(model): normalize model config identity 2026-05-16 16:47:18 +08:00
linshen c718d78ed4 fix(provider): pass Chrome Prompt API language options 2026-05-16 22:00:33 +08:00
linshen 4340f1bf28 feat(provider): add Chrome built-in AI support
- Register Chrome built-in AI as a local text provider with availability checks.
- Add explicit setup/download gating and auto-enable safeguards.
- Preserve structured prompt roles through initialPrompts and stream tests.
2026-05-16 11:29:46 +08:00
linshen b691f4f2c1 fix(core): keep local providers disabled by default
- Keep no-key and local model sources disabled until explicit user configuration exists.
- Tighten default text and image model enablement checks.
- Cover environment-driven defaults for local providers.
2026-05-16 09:47:21 +08:00
linshen 684a7bf4c1 feat(provider): add Grok text and image support
- Add first-class xAI/Grok text and image adapters with dynamic model fallback.
- Register defaults, env mapping, docs, locale labels, and legacy converter handling.
- Cover Grok request payloads, image defaults, registry behavior, and input image limit checks.
2026-05-15 20:43:18 +08:00
linshen 5e942ca945 feat: polish provider controls and themed UI
- Add provider pill selection and normalized provider display copy

- Adopt themed tooltips, confirmation dialogs, and Naive UI surface styles

- Enable Prompt Garden thumbnail previews through shared image preview components
2026-05-14 21:18:43 +08:00
linshen d08494f6b6 refactor: clarify built-in template labels 2026-05-13 21:37:24 +08:00
linshen 95a030ebe0 fix(model): preserve literal strings in Python JSON normalization
Normalize Python-style JSON literals only outside quoted strings.

Preserve values like "False" and escaped literal words inside JSON strings.

Cover mixed string and unquoted literal custom parameter values.
2026-05-13 21:05:46 +08:00
SamCheng0717 1df08bc2e5 fix(model): support JSON custom parameter values
- Parse Python-style JSON literals for custom model parameters

- Add JSON/string format controls for custom parameter inputs

- Add model parameter docs and locale strings
2026-05-13 21:03:26 +08:00
linshen ce26772cad fix(template): preserve variables in prompt templates
- Instruct default templates to keep variable placeholders intact

- Apply the guardrail across text, context, image, and iteration templates

- Extend preservation coverage for JSON-structure image prompts
2026-05-13 19:47:33 +08:00
linshen f25837b6cb feat(ui): polish workspace controls and source cues
- Link test source cues back to prompt panel areas

- Add source-linked cards, variant tags, and feedback composables

- Add image model quick switching and workspace control polish
2026-05-12 21:36:52 +08:00
linshen 69db225a1a feat(model): support headers and text quick switching
- Add custom request header parsing and provider metadata resolution

- Add quick switching controls for text model workspaces

- Keep model UI labels and custom header output tidy
2026-05-10 23:08:14 +08:00
linshen efda7828b8 fix(ui): wire image workspace analysis actions 2026-05-10 15:20:00 +08:00
linshen 9711acb424 feat(image): support OpenAI multi-image edits 2026-05-09 20:47:39 +08:00
linshen 50b05a0868 fix: normalize LLM image inputs 2026-05-06 23:37:23 +08:00
linshen 1390a24e13 fix(ui): honor optional prompt asset variables 2026-05-05 21:20:00 +08:00
linshen 0c9ddd5063 fix(data): include image model configs in backups
Include image model configuration data in app-wide export/import flows and initialize the image model manager before wiring backup services.
2026-05-03 13:15:18 +08:00
linshen 2d8720247f fix(electron): serialize IPC payloads safely
Sanitize Electron IPC payloads for data, image, and Garden favorite import paths so reactive objects do not cross the process boundary.
2026-05-03 13:15:17 +08:00
linshen 6d75528793 feat(prompt-garden): integrate import and favorite flow
Wire Prompt Garden imports into workspace and favorite flows, add the import dialog/panel affordances, persist Garden metadata/media into favorites, and document the external import contract.
2026-05-03 13:15:16 +08:00
linshen 4accdf1417 feat(prompt-garden): add discovery import entry
- Add environment defaults and Vite proxy configuration for Prompt Garden discovery
- Expose discovery import controls from workspace utility surfaces
- Wire image text-to-image import affordances and localized copy
- Document configuration and cover environment/UI behavior with tests
2026-05-02 22:20:01 +08:00
linshen 743e622f6c feat(ui): use filled variables as generation context
- Pass existing filled variable values into smart value generation
- Update generation templates and service contracts for context-aware output
- Cover service runtime and UI composable behavior with targeted tests
2026-05-02 22:20:00 +08:00
linshen 11a817f833 feat(favorites): manage prompt asset versions
- Store and expose prompt-asset version history through core and desktop bridges
- Add version browsing and preview surfaces to the favorite editor/detail UI
- Simplify version navigation around a dedicated preview modal
- Cover version persistence and UI behavior with focused regressions
2026-05-01 19:18:33 +08:00
linshen 23848a840d feat(favorites): refine prompt asset workspace flows
- Bind favorites to source assets and save targets throughout workspace actions
- Share the favorite editor/detail surfaces across dialogs and workspace panels
- Add provenance badges, utility-menu apply actions, and themed favorite panels
- Expand unit and integration coverage for favorite source and editor flows
2026-05-01 14:36:12 +08:00
linshen 93377e1b70 feat(favorites): standardize prompt asset sessions
- Add prompt-model services for content, examples, modes, sessions, and history
- Persist richer favorite prompt-asset metadata and session projections
- Wire favorite save/apply paths across supported workspaces
- Cover the new prompt-asset contract with core and UI regressions
2026-05-01 10:24:18 +08:00
linshen 4910e03d1f fix(ui): clarify minimax api endpoint guidance 2026-04-26 23:06:50 +08:00
linshen d2e1473658 feat(core): refresh openai image provider models 2026-04-26 22:47:54 +08:00
linshen d315c4da22 fix(core): clarify image prompt JSON wrapper handling
Avoid treating placeholder-based natural language prompts as structured JSON so image prompt templates preserve the intended output format.
2026-04-26 18:47:13 +08:00
linshen faeee9ff4c feat(core): update DeepSeek provider for v4 models 2026-04-24 22:35:32 +08:00
linshen 49ddd1ca56 feat(core): add structured SOUL templates for OpenClaw and Hermes 2026-04-23 21:38:31 +08:00
linshen 2e119a6d83 fix(core): align seedream image model capabilities 2026-04-20 22:26:52 +08:00
linshen 713143d47b feat(models): add responses request style for openai apis 2026-04-15 21:47:23 +08:00
linshen 54fbd76685 fix(i18n): restore locale defaults and localized feedback
- restore locale bootstrap defaults across UI and MCP startup paths
- localize template, context editor, favorites, Prompt Garden, and history feedback toasts
- isolate UI consumer typechecks needed by the localization rollout
- add regression tests covering english-first runtime behavior and localized fallbacks
2026-04-09 22:17:34 +08:00