1437 Commits
Author SHA1 Message Date
Toshii fa8491b3aa remove log (#4040) 2025-06-04 18:53:12 -07:00
pashpashpashandCline Evaluation b811db823b Option to disable aggressive terminal reuse for users affected by the task lockout bug. (#4041)
* terminal setting for reusing terminal commands

* language

* changeset

* changeset language

* comment clarity

---------

Co-authored-by: Cline Evaluation <cline@example.com>
2025-06-04 18:52:53 -07:00
Sarah Fortune 4f7dc6fb36 Add a postMessage handler for standalone cline app (#4038)
* Add a postMessage handler for standalone cline app.

If there is no vscode api defined, try to use the standalone post
Message handler.

* Imports

* Update logs
2025-06-04 17:44:38 -07:00
Sarah Fortune b7096a77db Add type checking for protobus RPC handlers. (#4020)
* Add type checking for protobus RPC handlers.

Add type parameters to the wrapper function when generating the server-setup file.
So that the parameters of the RPC handler will be type checked against types defined in the service.
The generated code looks like this:
```
    server.addService(proto.cline.CheckpointsService.service, {
         checkpointDiff: wrapper<cline.Int64Request,cline.Empty>(checkpointDiff, controller),
         checkpointRestore: wrapper<cline.CheckpointRestoreRequest,cline.Empty>(checkpointRestore, controller),
    });
```

Add an index.ts file to the proto directory so all the proto types can be imported without having to know which proto message is defined in which file (the proto descriptor set doesn't have this information).

* Generate index.ts with protoc instead of doing it ourselves.

Turn on the option 'dontExportCommonSymbols' in protoc, so that each generated proto file is not trying to export the same utility functions.

Generate all the protos with the same protoc command.

* cleanup
2025-06-04 17:42:19 -07:00
cbcd17764b Protobus Host Bridge (#3747)
* WIP host bridge

* Run formatter

* remove tmp impl & rename host grpc client

* gitignore more files

* better layout

* host handler to make other hosts easier to add

* remove adapter pattern

* get host responses correctly

* fix streaming mode for host bridge

* first wip subscription host bridge demo for watching mcp server config

* format, comment

* add cancellation for host grpc stream

* remove unneeded functions from host-grpc-handler

* add a method for canceling request rather than using the registry

* another todo

* use StringRequest for uri.proto

* debounce new file watcher

* remove test setup

* remove some todos and logs

* remove registry use todo

* Revert "remove registry use todo"

This reverts commit 84078d3469.

* fix capitalization of uri.proto

* a better pattern for a callback based bridge without using the requestRegistry directly

---------

Co-authored-by: Andrei Edell <andrei@nugbase.com>
Co-authored-by: Sarah Fortune <sarah.fortune@gmail.com>
Co-authored-by: Andrei Eternal <eternal@cline.bot>
2025-06-04 15:41:30 -07:00
EvanandElephant Lumps 586eb3cd9e migrate accountButtonClicked (#4008)
Co-authored-by: Elephant Lumps <celestial_vault@Elephants-MacBook-Pro.local>
2025-06-04 11:40:52 -07:00
Steven White 584535393f New AskSage Models (#3780)
* chore: new AskSage models

* chore: add changeset
2025-06-04 11:21:18 -07:00
01a9ab0cf6 feat: add all qwen3 models support and add thinking mode options (#3692)
* feat: add all qwen3 models support and add thinking mode options

* fix: qwen model reasoning logic configuration, set the qwen model maxBudget value

* fix: correct the maxTokens in qwen3 model

* vertex model

---------

Co-authored-by: xuanqi <xuanqi.cc@alibaba-inc.com>
Co-authored-by: 0xtoshii <94262432+0xToshii@users.noreply.github.com>
2025-06-04 09:08:48 -07:00
Sarah Fortune 51a538373f Make the protobuf object literal lint check an error instead of a warning. (#4019)
Fix remaining occurences of protobuf literals.
2025-06-03 23:58:52 -07:00
canvrno a6ce75d17c Telemetry fix (#4009) 2025-06-03 18:44:52 -07:00
EvanandElephant Lumps 0a3d0e3569 Migrate chatbuttonclicked protobus (#3854)
* migrate chatButtonClicked

* changeset

* send targeted event to the controller

* prettier

* add test mock

* continue to fix tests

* fix test mocks once and for all

* fix test mocks once and for all

* try again please lord

* try again

* temporarily disable tests

* revert other test 'fixes'

* one more

---------

Co-authored-by: Elephant Lumps <celestial_vault@Elephants-MacBook-Pro.local>
2025-06-03 14:47:08 -07:00
Sarah Fortune fccac277d2 feat(lint): Add custom ESLint rule for checking that protobuf messages are created using .create() in more contexts (#3929)
* feat(lint): Add custom ESLint rules for protobuf type checking

Add two custom ESLint rules to enforce proper usage patterns when creating protobuf objects.

Using .create() to build protobufs ensures that the protobuf is type checked when it is created. Protobufs created using
object literals are not type checked,  which can lead to subtle bugs and type mismatches. The linter rules detect when protobufs are created without using .create() or .fromPartial().

- no-protobuf-object-literals: Enforces the use of `.create()` or `.fromPartial()` methods instead of object literals when creating protobuf types.

```
/Users/sjf/cline/src/shared/proto-conversions/state/chat-settings-conversion.ts
   9:9  warning  Use ChatSettings.create() or ChatSettings.fromPartial() instead of object literal for protobuf type
Found: return {
             mode: chatSettings.mode === "plan" ? PlanActMode.PLAN : PlanActMode.ACT,
             preferredLanguage: chatSettings.preferredLanguage,
             openAiReasoningEffort: chatSettings.openAIReasoningEffort,
     }
  Suggestion: ChatSettings.create({
             mode: chatSettings.mode === "plan" ? PlanActMode.PLAN : PlanActMode.ACT,
             preferredLanguage: chatSettings.preferredLanguage,
             openAiReasoningEffort: chatSettings.openAIReasoningEffort,
     })
```

- no-grpc-client-object-literals: Enforces proper protobuf creation for gRPC service client parameters. This needs a separate rule
because the type signatures of the ServiceClients methods are too generic to be detected by the previous rule.

```
/Users/sjf/cline/webview-ui/src/components/mcp/configuration/tabs/add-server/AddRemoteServerForm.tsx
   41:62  warning  Use the appropriate protobuf .create() or .fromPartial() method instead of object literal for gRPC client parameters.
Found: McpServiceClient.addRemoteMcpServer({
                             serverName: serverName.trim(),
                             serverUrl: serverUrl.trim(),
                     })
```

These rules help maintain code quality by enforcing consistent patterns for working with protocol buffers throughout the codebase, reducing potential runtime errors from improper message construction.

* Update test

* Add custom eslint rules to new webview-ui config

* formatting

* stuff

* undo protobuf fixes

* update rule

* update rule

* protobuf fixes

* rename unused params

* formatting
2025-06-03 14:21:54 -07:00
Paul Gear 00901e01b7 Change Ollama model selector to filterable dropdown (#3999)
* use dropdown for Ollama model list when possible

Code changes by Qwen3 30B A3B, based on OpenRouterModelPicker

* Document libasound2 and libnss3 test dependencies, sort list

* add test for OllamaModelPicker

Code by Claude Sonnet 3.7

* Add changeset
2025-06-03 13:52:50 -07:00
Sarah Fortune 4a3f5c4f69 Add globalState to the standalone vscode extension context replacement. (#3987)
* Add globalState to the standalone vscode extension context replacement.

Add a generic key-value store that can be used by different storages, and move this into vscode-context-utils file.
Move the stubs/mocks into a separate stubs file, (they have type checking turned off).
Keep the implementations in vscode-context and turn on typechecking for this file.

* Add type parameter for the values in the JsonKeyValueStore

* Optimize imports

* Add implementations for the vscode ExtensionContext in the standalone app (#4000)

* Formatting

* add package-lock.json
2025-06-03 12:06:13 -07:00
Michael 9f85105186 Add retry logic to API handlers with @withRetry decorator (#3596) 2025-06-03 10:19:14 -07:00
AraandCline Evaluation 8cbf25c026 Adding support for Streamable MCP server (#3970)
* Fixing OpenAI compatible to support cache token display

* Removing redundant logging and write to file

* Removing redundant logging and write to file

* Splitting constants

---------

Co-authored-by: Cline Evaluation <cline@example.com>
2025-06-03 00:29:45 -07:00
pashpashpashandCline Evaluation 82d0ac2088 Cozy Claude 4 (#3995)
* making claude4 feel better

* system prompt whoops

* small system prompt change

---------

Co-authored-by: Cline Evaluation <cline@example.com>
2025-06-02 19:28:35 -07:00
canvrno 8171b887ad Fix for checkpoints (#3993) 2025-06-02 18:25:44 -07:00
pashpashpashandCline Evaluation 203f805548 Claude 4 - experimental flag - defaults to classic function calling with some minor changes to system prompt (#3994)
* adding modularized flag for new claude4 experimental tools, default OFF

* diff.ts

* responses.ts

* system.ts

* tests and prompt

* forgot some chars

---------

Co-authored-by: Cline Evaluation <cline@example.com>
2025-06-02 18:22:38 -07:00
Nigel Packer c91ec4c97d Remove hard-coded temperature from LM Studio API requests and add support for easoning_content in LM Studio API responses. (#3971) 2025-06-02 18:18:13 -07:00
EvanandElephant Lumps d85c8ceeb2 migrate historyButtonClicked to protobus (#3977)
* migrate historyButtonClicked

* add webview provider type filtering

---------

Co-authored-by: Elephant Lumps <celestial_vault@Elephants-MacBook-Pro.local>
2025-06-02 15:23:19 -07:00
EvanandElephant Lumps b38994f1e8 Migrate mcpButtonClicked protobus (#3975)
* migrate mcpButtonClicked

* changeset

* only send event to matching webview type

---------

Co-authored-by: Elephant Lumps <celestial_vault@Elephants-MacBook-Pro.local>
2025-06-02 12:38:30 -07:00
AraandCline Evaluation d846c2cce9 Removing redundant logging and write to file (#3981)
Co-authored-by: Cline Evaluation <cline@example.com>
2025-06-02 08:58:13 +05:30
Adel Khial 6e50778db7 Add DeepSeek-R1-0528 to Nebius AI Studio API (#3973)
* Add DeepSeek-R1-0528 to Nebius AI Studio model list

* Add changeset

* Fix max tokens
2025-06-01 16:17:10 -07:00
EvanandElephant Lumps 3a325a6445 Open the hood (#3949)
* add open disk conversation history button

* changeset

* change icon due to lack of artistic freedom

---------

Co-authored-by: Elephant Lumps <celestial_vault@Elephants-MacBook-Pro.local>
2025-06-01 14:51:07 -07:00
EvanandElephant Lumps 97c25cb35e Pass id to webview on creation (#3867)
* pass type of webview to webview

* changeset

---------

Co-authored-by: Elephant Lumps <celestial_vault@Elephants-MacBook-Pro.local>
2025-06-01 14:06:48 -07:00
suntpandToshii 0fb82c1975 fix:The POST requests of MCP's SSE server support setting headers. (#2969)
* fix:The POST requests of MCP's SSE server support setting headers.(#2652)

* fix:The POST requests of MCP's SSE server support setting headers.(#2652)

---------

Co-authored-by: Toshii <94262432+0xToshii@users.noreply.github.com>
2025-06-01 13:25:31 -07:00
pashpashpash 36c3f93884 added modelId to tool call events (#3968) 2025-06-01 13:24:12 -07:00
pashpashpash 3fb0360e01 fixing ripgrep overload - tool should not return more than 0.25mb max… (#3967)
* fixing ripgrep overload - tool should not return more than 0.25mb max, but it can easily return more than 9mb in some cases

* changeset
2025-06-01 13:24:00 -07:00
084c0a73a3 Apply new edit tool to diff (#3944)
* add ls file tool description, parsing, and return formatting

* add json tool definition and remove extra '.'

* changeset

* use separate function for new format

* using json

* add grep tool new format

* add editTool definition

* Map MultiEdit tool to StreamingJsonReplacer with logs

* Adding support for non streamed json

* Adding logging

* moving multiedit tool into tool defs

---------

Co-authored-by: Elephant Lumps <celestial_vault@Elephants-MacBook-Pro.local>
Co-authored-by: Cline Evaluation <cline@example.com>
Co-authored-by: pashpashpash <nik@nugbase.com>
2025-06-01 13:23:52 -07:00
AraandCline Evaluation 079d05c2cc Fixing OpenAI compatible to support cache token display (#3957)
Co-authored-by: Cline Evaluation <cline@example.com>
2025-06-01 05:55:31 +05:30
Ara acc795ed69 Fix pricing and token counting for Xai Provider for the new Grok 3 family of models (#3956) 2025-05-31 11:49:29 -07:00
Elon Gliksberg 1aaa30ecce Closing MCP processes when app terminates. (#3876) 2025-05-31 01:44:03 -07:00
Sarah Fortune f7e5398ac8 Fix warnings for protobuf object literals (#3948)
Create protobuf objects with .create()
2025-05-31 01:35:29 -07:00
Gustavo A. Rodríguez Suárezand0xtoshii 89f35b0800 Fix undefined type during chunk streaming (#1464)
* Fix undefined type when parsing response chunk in stream

* Fix undefined type when parsing response chunk in stream

* remove Cline.ts changes

---------

Co-authored-by: 0xtoshii <94262432+0xToshii@users.noreply.github.com>
2025-05-31 00:02:28 -07:00
Sarah Fortune 0c6a4f9452 feat(lint): Add custom ESLint rules for protobuf type checking for protobus ServiceClients (#3946)
* Fix linter warnings in the webview (part 2)

Replace protobus calls using object literals to use Message.create({...})

Fix incorrect property name detected after this change in webview-ui/src/components/settings/SettingsView.tsx

Optimised imports in vscode.

* formatting

* feat(lint): Add custom ESLint rules for protobuf type checking

Add two custom ESLint rules to enforce proper usage patterns when creating protobuf objects.

Using .create() to build protobufs ensures that the protobuf is type checked when it is created. Protobufs created using
object literals are not type checked,  which can lead to subtle bugs and type mismatches. The linter rules detect when protobufs are created without using .create() or .fromPartial().

- no-protobuf-object-literals: Enforces the use of `.create()` or `.fromPartial()` methods instead of object literals when creating protobuf types.

```
/Users/sjf/cline/src/shared/proto-conversions/state/chat-settings-conversion.ts
   9:9  warning  Use ChatSettings.create() or ChatSettings.fromPartial() instead of object literal for protobuf type
Found: return {
             mode: chatSettings.mode === "plan" ? PlanActMode.PLAN : PlanActMode.ACT,
             preferredLanguage: chatSettings.preferredLanguage,
             openAiReasoningEffort: chatSettings.openAIReasoningEffort,
     }
  Suggestion: ChatSettings.create({
             mode: chatSettings.mode === "plan" ? PlanActMode.PLAN : PlanActMode.ACT,
             preferredLanguage: chatSettings.preferredLanguage,
             openAiReasoningEffort: chatSettings.openAIReasoningEffort,
     })
```

- no-grpc-client-object-literals: Enforces proper protobuf creation for gRPC service client parameters. This needs a separate rule
because the type signatures of the ServiceClients methods are too generic to be detected by the previous rule.

```
/Users/sjf/cline/webview-ui/src/components/mcp/configuration/tabs/add-server/AddRemoteServerForm.tsx
   41:62  warning  Use the appropriate protobuf .create() or .fromPartial() method instead of object literal for gRPC client parameters.
Found: McpServiceClient.addRemoteMcpServer({
                             serverName: serverName.trim(),
                             serverUrl: serverUrl.trim(),
                     })
```

These rules help maintain code quality by enforcing consistent patterns for working with protocol buffers throughout the codebase, reducing potential runtime errors from improper message construction.

* Update test

* Add custom eslint rules to new webview-ui config

* Only include webview grpc ServiceClient check

* Fix lint errors

* formatting

* Update package-lock.json

* Update package.json
2025-05-30 20:19:04 -07:00
Daniel SteigmanandCopilot Autofix powered by AI 6626124bef fix(bedrock): resolve AWS credential caching issue with Identity Manager (#3936)
* fix(bedrock): resolve AWS credential caching issue with Identity Manager

- Add ignoreCache option for profile-based authentication to detect external credential file changes
- Implement smart caching for manual credentials with 5-minute TTL to maintain performance
- Add configuration hash-based cache invalidation for manual credential changes
- Add invalidateCredentialCache() method for error recovery scenarios

Fixes issue where AWS Identity Manager credential updates were not detected,
requiring extension restart. Profile-based authentication now always reads
fresh credentials while manual credentials maintain performance through caching.

Resolves credential refresh issues reported by users using AWS Identity Manager
with role-based authentication workflows.

* Potential fix for code scanning alert no. 66: Use of a broken or weak cryptographic algorithm

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>

* merge conflict

* updated to fixe the original medrock issue

---------

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
2025-05-30 19:11:20 -07:00
83928ccecc Add edit tool definition (#3939)
* add ls file tool description, parsing, and return formatting

* add json tool definition and remove extra '.'

* changeset

* use separate function for new format

* using json

* add grep tool new format

* add editTool definition

* removed changeset

* removed changeset

---------

Co-authored-by: Elephant Lumps <celestial_vault@Elephants-MacBook-Pro.local>
Co-authored-by: Cline Evaluation <cline@example.com>
2025-05-30 16:10:33 -07:00
Sarah Fortune 38a1179e62 Rename SecretStore.storeSecret to SecretStore.store (#3897)
Apparently ChatGPT can't follow the SDK docs.
2025-05-30 15:45:17 -07:00
Donovan Sydowand0xtoshii fb3012f778 add llama4 models, and mis/codestral models to vertex api (#3474)
* add llama4 models, and mis/codestral models to vertex api

* update mistral context window sizes

* changeset

---------

Co-authored-by: 0xtoshii <94262432+0xToshii@users.noreply.github.com>
2025-05-30 14:23:54 -07:00
pashpashpash 8336831d8f read tool + write tool + webfetch tool + question tool + usemcp tool + list code definition names tool + access MCP resource tool + load mcp documentation tool + attempt completion tool + browser tool + new task tool (#3925) 2025-05-30 13:16:37 -07:00
KevinTurnbulland0xtoshii ec064426b3 Minimal change to respect Ollama Context Window Size (#3880)
* Respect the CtxNum setting for Ollama Models

Currently since the context window size isn't respected for Ollama models - the LLM does a naive truncation which removes important details. This leads to the model entering endless loops or making unsupported edits when operating as an agent.

* small change

* changeset

---------

Co-authored-by: 0xtoshii <94262432+0xToshii@users.noreply.github.com>
2025-05-30 01:45:47 -07:00
canvrno 8f72bf11f7 optionsResponse protobus migration/removal (#3860) 2025-05-29 22:47:22 -07:00
pashpashpashandCline Evaluation 915cf76f85 Pashpashpash/bash tool (#3894)
* bashTool

* prettier

* alignment

* bashtool cont

* bash tool cont

* modularizing prompt a bit

* bash tool working

* bash tool now getting cwd

* bashTool

* forgot .name

---------

Co-authored-by: Cline Evaluation <cline@example.com>
2025-05-29 20:09:07 -07:00
Toshii f1fef24f25 support xlsx and csv (#3922) 2025-05-29 18:41:21 -07:00
Peter Dave Hello ceb0900bf6 Update xaiModels and xaiDefaultModelId in src/shared/api.ts (#3814) 2025-05-29 18:29:30 -07:00
e4e03fa0dd reverting timeout if no first chunk (#3899)
* reverting timeout if no first chunk

* Create fresh-days-end.md

---------

Co-authored-by: Cline Evaluation <cline@example.com>
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
2025-05-28 21:04:48 -07:00
pashpashpashandCline Evaluation 10892670be exact antml (#3891)
* exact antml

* only one invoke

* linter warnings

---------

Co-authored-by: Cline Evaluation <cline@example.com>
2025-05-28 19:12:26 -07:00
3c7a42c35d Add grep tool new format (#3893)
* add ls file tool description, parsing, and return formatting

* add json tool definition and remove extra '.'

* changeset

* use separate function for new format

* using json

* add grep tool new format

---------

Co-authored-by: Elephant Lumps <celestial_vault@Elephants-MacBook-Pro.local>
Co-authored-by: Cline Evaluation <cline@example.com>
2025-05-28 18:32:18 -07:00
abfaf6ca7a LS is moar (#3883)
* add ls file tool description, parsing, and return formatting

* add json tool definition and remove extra '.'

* changeset

* use separate function for new format

* using json

---------

Co-authored-by: Elephant Lumps <celestial_vault@Elephants-MacBook-Pro.local>
Co-authored-by: Cline Evaluation <cline@example.com>
2025-05-28 16:15:38 -07:00