docs: move release notes into CHANGELOG.md by sidharthmirch · Pull Request #70 · meltylabs/chorus

sidharthmirch · 2026-04-09T06:30:45Z

Summary

Move the fork release history out of README.md into a standalone CHANGELOG.md.
Include release entries for v0.14.5 through v0.14.15 plus 0.14.6-PRE in the changelog.
Update README.md to link to CHANGELOG.md from the fork changes section.

Test Plan

./node_modules/.bin/prettier --write README.md CHANGELOG.md
./node_modules/.bin/prettier --check README.md CHANGELOG.md

- New Visible Models settings tab: fetch models from OpenRouter/Ollama/LM Studio, then toggle per-model visibility with sub-provider filter chips - New Model Profiles settings tab: create/edit/delete named model sets grouped by provider; profiles draw only from visible models - Centralized filtering (ModelFiltering.ts) so visibility and active profile apply consistently in the chat model picker and quick chat - Profile selector dropdown in the chat model picker uses the themed Radix Select component Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Add Model Profiles and Visible Models management

Adds persona/role presets that inject a system prompt into chats. Includes 5 built-in profiles (Data Scientist, Academic Researcher, Study Guide, Code Reviewer, Creative Writer), a per-chat selector pill in the chat input toolbar, and a Prompt Profiles tab in Settings. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Add Model Profiles, Visible Models, and Prompt Profiles

- Created BUILD.md with instructions - Updated README.md - Added .github/workflows/build.yml - Removed unused import in ModelFiltering.ts Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

- Add LFS support to checkout step - Add Rust toolchain setup with caching via actions-rust-lang/setup-rust-toolchain@v1 - Use pnpm install --frozen-lockfile for deterministic builds - Remove push-to-main trigger to avoid duplicating cloud-qa.yaml - Upgrade pnpm/action-setup from v3 to v4 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

The updater bundle requires TAURI_SIGNING_PRIVATE_KEY which isn't available in CI. Build only app and dmg bundles for verification. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

--bundles flag doesn't suppress createUpdaterArtifacts; use --config inline override instead to prevent the signing key error. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Adds workflow_dispatch trigger with optional release_tag input. Builds for both aarch64 and x86_64 targets. When a release tag is provided, creates a GitHub Release with downloadable .app.zip and .dmg files for both architectures. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Add GitHub Release support to build workflow

- Migration v142: create Ambient Gemini Flash config (gemini-2.5-flash-preview-04-17, vision-capable, free tier on Google AI Studio), migrate users off the deprecated ambient-gemini-2.5-pro config, mark old config as deprecated - Remove ALLOWED_MODEL_IDS_FOR_QUICK_CHAT allowlist so all non-deprecated, enabled models with valid API keys appear in the ambient model selector Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

- Migration v143: add gemini-2.5-flash-lite (stable, vision-capable, free tier), deprecate gemini-2.0-flash-lite-preview-02-05, update ambient config to point to the new flash-lite model - Allow gemini-2.5-flash-lite in ProviderGoogle model name allowlist Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Bump @tauri-apps/plugin-store to ~2.2.0 to match the Rust crate which had already resolved to 2.2.0 via Cargo. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Ambient (quick chat) mode should not pass MCP tools like web_search to the model — there's no UI to invoke them and they cause confusing responses when the model tries to call an unconfigured tool. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Update ambient default to Gemini 2.5 Flash and open model selector

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Bump version to 0.14.6

Adds a "Select All" button in the profile selector row of the manage models dialog, plus a cmd+shift+A keyboard shortcut to select all currently visible models (respecting active profile and search filter). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Add Select All button and shortcut to model picker

… shortcut scope - Extract selectableVisibleModels memo shared by button and shortcut, filtering out models without API keys and OpenRouter when collapsed - Add `enabled` option to useShortcut so cmd+shift+A is not swallowed in non-default dialog modes Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

…lowup Fix Select All: filter ungated models, dedup logic, scope shortcut

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Bump version to 0.14.7

Users can now select which model is used to auto-generate chat titles. Defaults to the ambient chat model, with the option to pick from any cheap enabled OpenRouter model the user has marked available. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

…iders Refactor visible models settings by provider

- Fix migration ordering (142→143→144→145 instead of 142→144→145→143) - Check global YOLO before per-tool to skip unnecessary DB query - Fix checkToolYolo SELECT 1 typed as ToolYoloDBRow (now { exists }) - Add htmlFor/id to per-tool Label/Switch for accessibility - Make useAllToolYolo conditional (skip query when global YOLO is on) - Use yoloMode === false instead of !yoloMode to handle loading state - Remove stale useMemo with empty deps for allTools Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

… matching - Add parseSearchQuery to detect "provider: term" prefix syntax for hard provider filtering (e.g. "openai: gpt-4" shows only OpenAI models) - Replace isSubsequenceMatch with scoreMatch (exact > word-boundary > normalized substring; numeric terms require contiguous digit group match) - Update filterBySearch to accept providerFilter and sort by score - Update modelGroups useMemo to use parseSearchQuery and short-circuit non-matching provider groups Fixes false positives like "5.4" matching "4.6" or "420". Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

…ute scores - Use ProviderName[] for KNOWN_PROVIDERS to stay in sync with core model layer (adds "meta"; eliminates drift risk) - Guard against empty provider prefix (": gpt" no longer accidentally matches first provider in the list) - Require exact or unambiguous prefix match for provider (avoids "open:" being ambiguous between openai/openrouter) - Precompute scoreMatch per model in filterBySearch to avoid redundant work inside the sort comparator Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

…ty, and pre-send pricing UI Three features combined in one commit: 1. OpenRouter actual model + cost attribution - Add actual_model_id column to messages table (migration 145) - Persist actual routed model from OpenRouter generation API - Display actual model name with "via auto" badge in ToolsMessageView - Full data path: API -> DB -> ChatState -> MultiChat UI 2. Error-state cost reliability - Recompute and persist chat/project cost totals on error paths - Add cost invalidation in legacy onError and useStopMessageStreaming - Harden sidebar cost display with Number() coercion and Number.isFinite checks 3. Pre-send model pricing UI - Add formatPricePerMillion() utility to CostAPI - New ModelPricingDisplay component showing per-1M token pricing - Supports single-model and range display for multi-model compare - Integrated into ChatInput, respects showCost setting Made-with: Cursor

Apply Prettier formatting fixes for ModelPricingDisplay and ToolsMessageView so lint/style checks pass. Made-with: Cursor

Drop the chat-input model pricing display to keep the compose area uncluttered while preserving existing post-send cost behavior. Made-with: Cursor

The OpenRouter generation endpoint (/api/v1/generation) was returning negative total_cost values, and the actual model wasn't being captured. OpenRouter includes both usage.cost and the model field directly in the streaming response. This commit: - Captures chunk.model from the streaming response in ProviderOpenRouter - Reads usage.cost (OpenRouter extension) from the final chunk - Adds model and cost fields to the UsageData type - Prefers response-level cost/model in MessageAPI, falling back to the generation endpoint only when the response doesn't include them - Guards against negative cost values Made-with: Cursor

…ames Made-with: Cursor

…ibution-and-pricing-ui OpenRouter actual model attribution, error-state cost reliability, and pre-send pricing UI

Fix fuzzy search false positives in model picker

Add per-tool and per-project YOLO mode

chatgpt-codex-connector · 2026-04-09T06:30:51Z

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.

greptile-apps

Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.

Copilot

Pull request overview

This PR updates fork documentation/release history (adds CHANGELOG.md, updates README.md) while also introducing substantial new app functionality around model visibility/profiles/defaults, per-chat model selection persistence, and more granular YOLO permissions.

Changes:

Move fork release history into CHANGELOG.md, add BUILD.md, and adjust repo metadata/versioning.
Add model visibility controls + model/prompt profiles and consolidate defaults configuration under a new Settings “Defaults” tab.
Introduce per-tool/per-project YOLO overrides and related DB migrations + APIs.

Reviewed changes

Copilot reviewed 64 out of 65 changed files in this pull request and generated 9 comments.

Show a summary per file

File	Description
src/ui/lib/models.ts	Removes hardcoded quick-chat allowed model ID list.
src/ui/hooks/useShortcut.ts	Adds an `enabled` option to conditionally disable shortcuts.
src/ui/components/VisibleModelsTab.tsx	New Settings tab UI to manage per-model visibility, including provider sections and fetch actions.
src/ui/components/VisibleModelsTab.search.test.ts	Adds unit tests for visible-models search/filter helpers.
src/ui/components/visibleModelsSearch.ts	Implements provider/sub-provider parsing and model filtering logic for visibility UI.
src/ui/components/ui/textarea.tsx	Ensures Textarea has `w-full` styling.
src/ui/components/ui/command.tsx	Adds trailing content support to command input (e.g., shortcut hints).
src/ui/components/SortableColumnItem.tsx	Adds reusable draggable+dropspot component for sortable column behavior.
src/ui/components/Settings.tsx	Reworks Settings tabs (new tabs/order), adds title-generation model selector, routes legacy quick-chat tab to defaults, and wires in new tabs.
src/ui/components/QuickChatModelSelector.tsx	Switches quick-chat model selection to use centralized filtering + visibility map.
src/ui/components/PromptProfilesTab.tsx	Adds Settings UI to CRUD prompt profiles.
src/ui/components/PromptProfilePill.tsx	Adds chat toolbar pill to select/manage prompt profiles per chat.
src/ui/components/ProjectView.tsx	Adds per-project default prompt profile + per-project YOLO override selectors.
src/ui/components/PermissionsTab.tsx	Adds per-tool YOLO toggles when global YOLO is off.
src/ui/components/Onboarding.tsx	Updates onboarding to optionally collect multiple provider API keys.
src/ui/components/ModelProfilesTab.tsx	Adds Settings UI to CRUD model profiles (named model-config sets).
src/ui/components/ManageModelsBox.tsx	Adds profile selection/application, improved search (provider filter + scoring), and select-all shortcut wiring.
src/ui/components/DefaultsTab.tsx	New consolidated defaults tab for prompt/profile/model defaults + ambient chat settings.
src/ui/components/ChatInput.tsx	Adds collapsible input UX, per-chat model compare persistence + defaults application, minimized-model exclusion, and prompt profile pill.
src/ui/components/AutoExpandingTextarea.tsx	Adds `onHeightChange` callback to support collapse threshold logic.
src/ui/components/AppSidebar.tsx	Improves route parsing for chat ID and adds minimized-models sidebar panel with retry UX.
src/ui/App.tsx	Maps legacy `quick-chat` settings tab to `defaults` when opening settings.
src/core/utilities/Settings.ts	Adds new model/prompt default fields and seeds defaults via `buildFreshInstallModelAndPromptDefaults`.
src/core/utilities/ProxyUtils.ts	Treats whitespace-only API keys as absent.
src/core/utilities/ModelFiltering.ts	Adds centralized filtering utility for visibility + profile filtering.
src/core/utilities/ChorusDefaultPreferences.ts	Defines fresh-install defaults (e.g., Gemini 2.5 Flash Lite) for model-related settings.
src/core/infra/ToolsDisabledStore.ts	New zustand store for per-chat/per-model tool disable state.
src/core/infra/ModelOrderStore.ts	New zustand store for per-chat model order and current visual order.
src/core/infra/MinimizedModelsStore.ts	New zustand store tracking minimized model columns per chat.
src/core/chorus/ToolsetsManager.ts	Implements per-project and per-tool YOLO resolution precedence while preserving deny behavior.
src/core/chorus/ToolsetsManager.test.ts	Adds test ensuring always_deny blocks tool execution even with YOLO enabled.
src/core/chorus/Toolsets.ts	Adds MCP start/list tools timeouts and guards against concurrent start attempts.
src/core/chorus/simpleLLM.ts	Adds ability to route simpleLLM calls to a specific model config ID (for title gen).
src/core/chorus/prompts/prompts.ts	Adds prompt-profile system prompt injection hook.
src/core/chorus/Models.ts	Adds types for provider visibility, model profiles, prompt profiles; extends usage fields.
src/core/chorus/ModelProviders/simple/SimpleCompletionProviderFactory.ts	Adds `createProviderByPrefix` helper for targeted provider selection.
src/core/chorus/ModelProviders/ProviderOpenRouter.ts	Captures actual model + cost from streaming chunks into usage data.
src/core/chorus/ModelProviders/ProviderGoogle.ts	Adds support for `gemini-2.5-flash-lite`.
src/core/chorus/ChatState.ts	Adds `actualModelId` field on message state.
src/core/chorus/chatCreationDefaults.ts	Applies chat creation defaults (prompt profile for regular chats, ambient model for quick chats).
src/core/chorus/ChatCompareSelection.ts	Adds logic for computing initial compare selection using new defaults + visibility/profile filtering and syncing global compare metadata.
src/core/chorus/api/ToolYoloAPI.ts	Adds DB API + hooks for per-tool YOLO records.
src/core/chorus/api/ProviderVisibilityAPI.ts	Adds provider-visible-model persistence + visibility map helper that considers API-key gating.
src/core/chorus/api/PromptProfilesAPI.ts	Adds DB APIs + hooks for prompt profiles and per-chat associations.
src/core/chorus/api/ProjectAPI.ts	Extends project schema and adds mutations for default prompt profile + YOLO override; adds `fetchProjectYoloMode`.
src/core/chorus/api/ModelProfilesAPI.ts	Adds DB APIs + hooks for model profiles and active model profile.
src/core/chorus/api/ModelConfigChatAPI.ts	Adds per-chat saved compare selection resolution with fallback to ambient compare list.
src/core/chorus/api/CostAPI.ts	Captures OpenRouter `actualModel` for cost attribution.
src/core/chorus/api/ChatAPI.ts	Initializes per-chat compare selection on creation and applies creation defaults.
src-tauri/tauri.qa.conf.json	Bumps app version to 0.14.15 (QA config).
src-tauri/tauri.dev.conf.json	Bumps app version to 0.14.15 (dev config).
src-tauri/tauri.conf.json	Bumps app version to 0.14.15 (prod config).
src-tauri/src/migrations.rs	Adds new migrations (visibility/profiles/projects defaults) and legacy-compat migration 145/146 switch.
src-tauri/src/lib.rs	Adds runtime detection of legacy migration 145 and sets env var before running migrations.
README.md	Adds “Fork changes” section and links to `CHANGELOG.md`; links to `BUILD.md`.
package.json	Bumps version to 0.14.15 and updates plugin-store dependency.
CHANGELOG.md	New consolidated changelog for fork releases v0.14.5–v0.14.15 plus pre-release.
BUILD.md	New build instructions document.
.prettierignore	Adds `.context` to prettier ignore list.
.github/workflows/build.yml	Adds GitHub Actions build workflow with optional release creation.
.cursor/worktrees.json	Adds Cursor worktree setup command config.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-04-09T06:39:16Z

+    const isAllVisible = visibleProviderModels.every((m) => {
+        const v = visibleModels?.find((vm) => vm.modelId === m.modelId);
+        return v ? v.isVisible : true;
+    });


isAllVisible uses visibleModels?.find(...) inside an .every(...) over visibleProviderModels, making this O(n*m) per render. With large model lists this can become noticeably slow. Consider precomputing a Map/Set of visibility by modelId (e.g., via useMemo) and doing O(1) lookups.

Copilot · 2026-04-09T06:39:17Z

+# Fork changes
+
+-   Added profiles for favorite models in the chat window
+-   Dynamically fetch and select models from providers
+-   Prompt profiles: Choose your preferred chat persona


The PR title/description describe a docs-only change (moving release notes to CHANGELOG), but this diff includes substantial new UI + core functionality (models/profiles/YOLO/migrations/etc.). Please update the PR title/description (and ideally split into smaller PRs) so review scope and risk are clear.

Copilot · 2026-04-09T06:39:17Z

+    titleGenerationModelConfigId?: string;
 }

 export default function Settings({ tab = "general" }: SettingsProps) {


Because tab defaults to "general" in the function parameter, it’s never undefined. That means tab ?? resolvedTabParam will always prefer the prop and the ?tab= URL param (including the legacy quick-chat redirect) won’t take effect. Consider removing the default from the parameter and resolving defaultTab from the URL param when present.

Copilot · 2026-04-09T06:39:17Z

+                            <Input
+                                id={`${field.provider}-api-key`}
+                                placeholder={field.placeholder}
+                                value={apiKeyInputs[field.provider]}
+                                onChange={(event) =>


The onboarding API key <Input> fields don’t specify type="password", so keys will be shown in plaintext while typing. For API keys, consider masking by default (or providing an explicit show/hide toggle).

Copilot · 2026-04-09T06:39:18Z

+    const visibilityMap = new Map(
+        (data ?? []).map((v) => [v.modelId, v.isVisible]),
+    );


useProviderVisibilityMap creates a new Map(...) each render. Because callers often include this map in dependency arrays, this breaks memoization and can cause avoidable recomputation/rerenders. Consider wrapping the map construction in useMemo keyed on data, apiKeys, and allModels so the returned Map is referentially stable when inputs don’t change.

Copilot · 2026-04-09T06:39:18Z

+            const value = isVisible ? 1 : 0;
+            for (const modelId of modelIds) {
+                await db.execute(
+                    "INSERT OR REPLACE INTO provider_visible_models (provider_name, model_id, is_visible) VALUES (?, ?, ?)",
+                    [providerName, modelId, value],


useSetAllProviderModelsVisible awaits db.execute(...) inside a for loop, doing one write per model sequentially. For large catalogs (e.g., OpenRouter), this can be very slow. Consider batching in a transaction or using bulk insert semantics if available.

Copilot · 2026-04-09T06:39:18Z

+                            <Checkbox
+                                checked={allSelected}
+                                data-state={
+                                    someSelected && !allSelected
+                                        ? "indeterminate"
+                                        : undefined
+                                }


The provider-level checkbox sets data-state="indeterminate", but Radix Checkbox determines indeterminate state from the checked prop (it should be "indeterminate", not false). With the current code, the checkbox will likely render unchecked even when someSelected && !allSelected. Consider setting checked to "indeterminate" in that case and dropping the manual data-state.

Copilot · 2026-04-09T06:39:18Z

+    const allToolsDependency = ToolsetsManager.instance
+        .listToolsets()
+        .map(
+            (toolset) =>
+                `${toolset.name}:${toolset


allToolsDependency is built by calling ToolsetsManager.instance.listToolsets() (+ listTools()) on every render, and then listToolsets() is called again inside the useMemo. This duplicates potentially expensive work. Consider computing the tool list once (or exposing a stable tool list from ToolsetsManager) and deriving both the dependency and allTools from that single computation.

Copilot · 2026-04-09T06:39:19Z

+  build:
+    runs-on: macos-latest
+    permissions:
+      contents: write


The workflow grants contents: write on the pull_request trigger. Even if GitHub restricts GITHUB_TOKEN on forked PRs, this is a higher-risk default for PR builds. Consider least-privilege permissions for PR runs and limiting write permissions to the release workflow/job.

sidharthmirch and others added 30 commits March 29, 2026 00:21

Merge pull request #1 from sidharthmirch/claude/prompt-profiles

b8de3d0

Add Model Profiles and Visible Models management

Merge pull request #2 from sidharthmirch/claude/prompt-profiles

792af55

Add Model Profiles, Visible Models, and Prompt Profiles

Document fork changes in README

1f9f183

Add build instructions and CI/CD workflow

e2fe4cb

- Created BUILD.md with instructions - Updated README.md - Added .github/workflows/build.yml - Removed unused import in ModelFiltering.ts Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Apply consistent formatting

233474d

Fix lint error in VisibleModelsTab

a8f6beb

Skip updater artifact in CI build to avoid signing requirement

6bc3e04

The updater bundle requires TAURI_SIGNING_PRIVATE_KEY which isn't available in CI. Build only app and dmg bundles for verification. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Disable updater artifact creation in CI via config override

3441701

--bundles flag doesn't suppress createUpdaterArtifacts; use --config inline override instead to prevent the signing key error. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Merge pull request #3 from sidharthmirch/sidharthmirch/build-prod-app

42b8acd

Merge pull request #4 from sidharthmirch/sidharthmirch/build-prod-app

604dc9e

Add GitHub Release support to build workflow

Fix tauri-plugin-store version mismatch warning

ad0bf0d

Bump @tauri-apps/plugin-store to ~2.2.0 to match the Rust crate which had already resolved to 2.2.0 via Cargo. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Merge pull request #5 from sidharthmirch/claude/ambient-model-update

c176f49

Update ambient default to Gemini 2.5 Flash and open model selector

Bump version: patch to 0.14.6

2b44292

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Merge pull request #6 from sidharthmirch/sidharthmirch/v0.14.6

756150d

Bump version to 0.14.6

Fix Prettier formatting in ChatInput.tsx

7801de8

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Merge pull request #7 from sidharthmirch/sidharthmirch/select-all-models

95e3ba1

Add Select All button and shortcut to model picker

Merge pull request #8 from sidharthmirch/sidharthmirch/select-all-fol…

a9f3895

…lowup Fix Select All: filter ungated models, dedup logic, scope shortcut

Bump version to 0.14.7

6eb6e38

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Merge pull request #9 from sidharthmirch/sidharthmirch/publish-release

7531cdd

Bump version to 0.14.7

Update README

b28f086

sidharthmirch and others added 24 commits April 7, 2026 23:53

Merge pull request #25 from sidharthmirch/sidharthmirch/settings-prov…

2451a2d

…iders Refactor visible models settings by provider

style: format pricing and model header components with prettier

1234643

Apply Prettier formatting fixes for ModelPricingDisplay and ToolsMessageView so lint/style checks pass. Made-with: Cursor

revert: remove pre-send pricing UI from composer

a234373

Drop the chat-input model pricing display to keep the compose area uncluttered while preserving existing post-send cost behavior. Made-with: Cursor

fix(ui): only show via-auto when model truly differs

6062fa7

fix(ui): autorouter/freerouter labels and resolve free-tier display n…

138e909

…ames Made-with: Cursor

Merge pull request #31 from sidharthmirch/claude/openrouter-cost-attr…

3c29332

…ibution-and-pricing-ui OpenRouter actual model attribution, error-state cost reliability, and pre-send pricing UI

fix: improve visible model sub-provider search

59cb688

feat: allow selecting multiple sub-provider filters

690b9bf

Fix MCP terminal startup and ignore .context in Prettier

c779034

Merge origin/main and resolve migrations conflict

4eaf9e9

Address Copilot review feedback on model search

3a39b25

Keep selected provider chips visible during search

fa14b6e

Merge pull request #29 from sidharthmirch/sidharthmirch/fix-fuzzy-search

d649b86

Fix fuzzy search false positives in model picker

Fix YOLO deny precedence and memoize permission tool list

9256b88

Add migration 145 legacy compatibility for dev instances

a374236

Format tool permission files with Prettier

0cd1a1f

Merge pull request #28 from sidharthmirch/sidharthmirch/per-tool-yolo

4a1c2c4

Add per-tool and per-project YOLO mode

chore: prepare v0.14.15 release

b2fc2b4

docs: split changelog into standalone file

4f34230

Copilot AI review requested due to automatic review settings April 9, 2026 06:30

greptile-apps Bot reviewed Apr 9, 2026

View reviewed changes

Copilot started reviewing on behalf of sidharthmirch April 9, 2026 06:31 View session

Copilot AI reviewed Apr 9, 2026

View reviewed changes

sidharthmirch closed this Apr 9, 2026

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

docs: move release notes into CHANGELOG.md#70

docs: move release notes into CHANGELOG.md#70
sidharthmirch wants to merge 130 commits into
meltylabs:mainfrom
sidharthmirch:sidharthmirch/v0.14.15-release

sidharthmirch commented Apr 9, 2026

Uh oh!

chatgpt-codex-connector Bot commented Apr 9, 2026

Uh oh!

greptile-apps Bot left a comment

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Apr 9, 2026

Uh oh!

Copilot AI Apr 9, 2026

Uh oh!

Copilot AI Apr 9, 2026

Uh oh!

Copilot AI Apr 9, 2026

Uh oh!

Copilot AI Apr 9, 2026

Uh oh!

Copilot AI Apr 9, 2026

Uh oh!

Copilot AI Apr 9, 2026

Uh oh!

Copilot AI Apr 9, 2026

Uh oh!

Copilot AI Apr 9, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Conversation

sidharthmirch commented Apr 9, 2026

Summary

Test Plan

Uh oh!

chatgpt-codex-connector Bot commented Apr 9, 2026

Uh oh!

greptile-apps Bot left a comment

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Apr 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 9, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants