Julia Ryan
ef5b8c6fed
We've been considering removing workspace-hack for a couple reasons: - Lukas ran into a situation where its build script seemed to be causing spurious rebuilds. This seems more likely to be a cargo bug than an issue with workspace-hack itself (given that it has an empty build script), but we don't necessarily want to take the time to hunt that down right now. - Marshall mentioned hakari interacts poorly with automated crate updates (in our case provided by rennovate) because you'd need to have `cargo hakari generate && cargo hakari manage-deps` after their changes and we prefer to not have actions that make commits. Currently removing workspace-hack causes our workspace to grow from ~1700 to ~2000 crates being built (depending on platform), which is mainly a problem when you're building the whole workspace or running tests across the the normal and remote binaries (which is where feature-unification nets us the most sharing). It doesn't impact incremental times noticeably when you're just iterating on `-p zed`, and we'll hopefully get these savings back in the future when rust-lang/cargo#14774 (which re-implements the functionality of hakari) is finished. Release Notes: - N/A
263 lines
12 KiB
JSON
263 lines
12 KiB
JSON
{
|
|
"completion_mode": "normal",
|
|
"cumulative_token_usage": {
|
|
"cache_creation_input_tokens": 18383,
|
|
"cache_read_input_tokens": 97250,
|
|
"input_tokens": 45,
|
|
"output_tokens": 776
|
|
},
|
|
"detailed_summary_state": "NotGenerated",
|
|
"exceeded_window_error": null,
|
|
"initial_project_snapshot": {
|
|
"timestamp": "2025-05-08T14:31:16.701157512Z",
|
|
"unsaved_buffer_paths": [],
|
|
"worktree_snapshots": [
|
|
{
|
|
"git_state": {
|
|
"current_branch": null,
|
|
"diff": "diff --git a/crates/language_model_selector/src/language_model_selector.rs b/crates/language_model_selector/src/language_model_selector.rs\nindex 6775bee98a..e25c9e1415 100644\n--- a/crates/language_model_selector/src/language_model_selector.rs\n+++ b/crates/language_model_selector/src/language_model_selector.rs\n@@ -410,7 +410,8 @@ impl ModelMatcher {\n }\n \n pub fn is_match(self: &Self, info: &ModelInfo) -> bool {\n- self.matched_ids.contains(&info.model.id().0)\n+ let q = (info.model.provider_id(), info.model.id());\n+ self.matched_models.contains(&q)\n }\n }\n \n",
|
|
"head_sha": "9245656485e58a5d6d717d82209bc8c57cb9c539",
|
|
"remote_url": "git@github.com:zed-industries/zed.git"
|
|
},
|
|
"worktree_path": "/home/silver/develop/zed"
|
|
}
|
|
]
|
|
},
|
|
"messages": [
|
|
{
|
|
"context": "\n<context>\nThe following items were attached by the user. They are up-to-date and don't need to be re-read.\n\n<files>\n```rs zed/crates/language_model_selector/src/language_model_selector.rs\nconst TRY_ZED_PRO_URL [L28]\ntype OnModelChanged [L30]\ntype GetActiveModel [L31]\npub struct LanguageModelSelector [L33-37]\n picker [L34]\n _authenticate_all_providers_task [L35]\n _subscriptions [L36]\nimpl LanguageModelSelector [L39-231]\n pub fn new [L40-81]\n fn handle_language_model_registry_event [L83-104]\n fn authenticate_all_providers [L110-154]\n fn all_models [L156-204]\n pub fn active_model [L206-208]\n fn get_active_model_index [L210-230]\nimpl EventEmitter<DismissEvent> for LanguageModelSelector [L233]\nimpl Focusable for LanguageModelSelector [L235-239]\n fn focus_handle [L236-238]\nimpl Render for LanguageModelSelector [L241-245]\n fn render [L242-244]\npub struct LanguageModelSelectorPopoverMenu [L248-258]\n language_model_selector [L253]\n trigger [L254]\n tooltip [L255]\n handle [L256]\n anchor [L257]\nimpl LanguageModelSelectorPopoverMenu<T, TT> [L260-284]\n pub fn new [L265-278]\n pub fn with_handle [L280-283]\nimpl RenderOnce for LanguageModelSelectorPopoverMenu<T, TT> [L286-304]\n fn render [L291-303]\nstruct ModelInfo [L307-310]\n model [L308]\n icon [L309]\npub struct LanguageModelPickerDelegate [L312-319]\n language_model_selector [L313]\n on_model_changed [L314]\n get_active_model [L315]\n all_models [L316]\n filtered_entries [L317]\n selected_index [L318]\nstruct GroupedModels [L321-324]\n recommended [L322]\n other [L323]\nimpl GroupedModels [L326-385]\n pub fn new [L327-342]\n fn entries [L344-370]\n fn model_infos [L372-384]\nenum LanguageModelPickerEntry [L387-390]\n Model [L388]\n Separator [L389]\nstruct ModelMatcher [L392-396]\n models [L393]\n bg_executor [L394]\n candidates [L395]\nimpl ModelMatcher [L398-452]\n fn new [L399-406]\n pub fn fuzzy_search [L408-424]\n pub fn exact_search [L426-438]\n fn make_match_candidates [L440-451]\nimpl PickerDelegate for LanguageModelPickerDelegate [L454-693]\n type ListItem [L455]\n fn match_count [L457-459]\n fn selected_index [L461-463]\n fn set_selected_index [L465-468]\n fn can_select [L470-480]\n fn placeholder_text [L482-484]\n fn update_matches [L486-546]\n fn confirm [L548-560]\n fn dismissed [L562-566]\n fn render_match [L568-636]\n fn render_footer [L638-692]\n\nShowing symbols 1-71 (total symbols: 71)\n\n```\n</files>\n</context>\n",
|
|
"creases": [
|
|
{
|
|
"end": 140,
|
|
"icon_path": "icons/file_icons/rust.svg",
|
|
"label": "language_model_selector.rs",
|
|
"start": 38
|
|
}
|
|
],
|
|
"id": 0,
|
|
"role": "user",
|
|
"segments": [
|
|
{
|
|
"text": "I recently introduced fuzzy search in [@language_model_selector.rs](@file:zed/crates/language_model_selector/src/language_model_selector.rs). Can you write unit-test that check it? You can find a test list of models on images. ",
|
|
"type": "text"
|
|
}
|
|
],
|
|
"tool_results": [],
|
|
"tool_uses": []
|
|
},
|
|
{
|
|
"context": "",
|
|
"creases": [],
|
|
"id": 1,
|
|
"role": "assistant",
|
|
"segments": [
|
|
{
|
|
"text": "I'll help you write unit tests for the fuzzy search functionality in the language model selector. I see that you want to test the fuzzy search with the models shown in the images - both Claude models (3, 3.5, 3.7) and GPT models (GPT-3.5, GPT-4, GPT-4o, etc.).\n\nLet's start by examining the code structure to understand how the fuzzy search works.",
|
|
"type": "text"
|
|
}
|
|
],
|
|
"tool_results": [
|
|
{
|
|
"content": "zed/crates/language_model_selector/Cargo.toml\nzed/crates/language_model_selector/LICENSE-GPL\nzed/crates/language_model_selector/src\n",
|
|
"is_error": false,
|
|
"output": null,
|
|
"tool_use_id": "toolu_01FvYMtHs763GL1wA5mpTpqn"
|
|
}
|
|
],
|
|
"tool_uses": [
|
|
{
|
|
"id": "toolu_01FvYMtHs763GL1wA5mpTpqn",
|
|
"input": {
|
|
"path": "zed/crates/language_model_selector"
|
|
},
|
|
"name": "list_directory"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"context": "",
|
|
"creases": [],
|
|
"id": 2,
|
|
"role": "assistant",
|
|
"segments": [
|
|
{
|
|
"text": "Let's look at the structure of the tests directory or see if there are existing tests:",
|
|
"type": "text"
|
|
}
|
|
],
|
|
"tool_results": [
|
|
{
|
|
"content": "zed/crates/language_model_selector/src/language_model_selector.rs\n",
|
|
"is_error": false,
|
|
"output": null,
|
|
"tool_use_id": "toolu_01KSLDsLLrf7tgixB1sge3cm"
|
|
}
|
|
],
|
|
"tool_uses": [
|
|
{
|
|
"id": "toolu_01KSLDsLLrf7tgixB1sge3cm",
|
|
"input": {
|
|
"path": "zed/crates/language_model_selector/src"
|
|
},
|
|
"name": "list_directory"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"context": "",
|
|
"creases": [],
|
|
"id": 3,
|
|
"role": "assistant",
|
|
"segments": [
|
|
{
|
|
"text": "Let's check the Cargo.toml to understand the dependencies:",
|
|
"type": "text"
|
|
}
|
|
],
|
|
"tool_results": [
|
|
{
|
|
"content": "[package]\nname = \"language_model_selector\"\nversion = \"0.1.0\"\nedition.workspace = true\npublish.workspace = true\nlicense = \"GPL-3.0-or-later\"\n\n[lints]\nworkspace = true\n\n[lib]\npath = \"src/language_model_selector.rs\"\n\n[dependencies]\ncollections.workspace = true\nfeature_flags.workspace = true\nfuzzy.workspace = true\ngpui.workspace = true\nlanguage_model.workspace = true\nlog.workspace = true\npicker.workspace = true\nproto.workspace = true\nui.workspace = true\n\nzed_actions.workspace = true\n",
|
|
"is_error": false,
|
|
"output": null,
|
|
"tool_use_id": "toolu_019Je2MLfJhpJr93g5igoRAH"
|
|
}
|
|
],
|
|
"tool_uses": [
|
|
{
|
|
"id": "toolu_019Je2MLfJhpJr93g5igoRAH",
|
|
"input": {
|
|
"path": "zed/crates/language_model_selector/Cargo.toml"
|
|
},
|
|
"name": "read_file"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"context": "",
|
|
"creases": [],
|
|
"id": 4,
|
|
"role": "assistant",
|
|
"segments": [
|
|
{
|
|
"text": "Now let's look at the fuzzy search implementation in detail:",
|
|
"type": "text"
|
|
}
|
|
],
|
|
"tool_results": [
|
|
{
|
|
"content": "struct ModelMatcher {\n models: Vec<ModelInfo>,\n bg_executor: BackgroundExecutor,\n candidates: Vec<StringMatchCandidate>,\n}\n\nimpl ModelMatcher {\n fn new(models: Vec<ModelInfo>, bg_executor: BackgroundExecutor) -> ModelMatcher {\n let candidates = Self::make_match_candidates(&models);\n Self {\n models,\n bg_executor,\n candidates,\n }\n }\n\n pub fn fuzzy_search(&self, query: &str) -> Vec<ModelInfo> {\n let matches = self.bg_executor.block(match_strings(\n &self.candidates,\n &query,\n false,\n 100,\n &Default::default(),\n self.bg_executor.clone(),\n ));\n\n let matched_models: Vec<_> = matches\n .into_iter()\n .map(|m| self.models[m.candidate_id].clone())\n .collect();\n\n matched_models\n }\n\n pub fn exact_search(&self, query: &str) -> Vec<ModelInfo> {\n self.models\n .iter()\n .filter(|m| {\n m.model\n .name()\n .0\n .to_lowercase()\n .contains(&query.to_lowercase())\n })\n .cloned()\n .collect::<Vec<_>>()\n }\n\n fn make_match_candidates(model_infos: &Vec<ModelInfo>) -> Vec<StringMatchCandidate> {\n model_infos\n .iter()\n .enumerate()\n .map(|(index, model)| {\n StringMatchCandidate::new(\n index,\n &format!(\"{}/{}\", &model.model.provider_id().0, &model.model.name().0),\n )\n })\n .collect::<Vec<_>>()\n }\n}",
|
|
"is_error": false,
|
|
"output": null,
|
|
"tool_use_id": "toolu_01GpKFEn6hYrXGiS5yBF3urk"
|
|
}
|
|
],
|
|
"tool_uses": [
|
|
{
|
|
"id": "toolu_01GpKFEn6hYrXGiS5yBF3urk",
|
|
"input": {
|
|
"end_line": 452,
|
|
"path": "zed/crates/language_model_selector/src/language_model_selector.rs",
|
|
"start_line": 392
|
|
},
|
|
"name": "read_file"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"context": "",
|
|
"creases": [],
|
|
"id": 5,
|
|
"role": "assistant",
|
|
"segments": [
|
|
{
|
|
"text": "Let's now check if there's an existing test module:",
|
|
"type": "text"
|
|
}
|
|
],
|
|
"tool_results": [
|
|
{
|
|
"content": "No matches found",
|
|
"is_error": false,
|
|
"output": null,
|
|
"tool_use_id": "toolu_01RZAvFvpMq16Dwh6d6cnVzy"
|
|
}
|
|
],
|
|
"tool_uses": [
|
|
{
|
|
"id": "toolu_01RZAvFvpMq16Dwh6d6cnVzy",
|
|
"input": {
|
|
"include_pattern": "zed/crates/language_model_selector/**/*.rs",
|
|
"regex": "mod tests"
|
|
},
|
|
"name": "grep"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"context": "",
|
|
"creases": [],
|
|
"id": 6,
|
|
"role": "assistant",
|
|
"segments": [
|
|
{
|
|
"text": "Now I'll create a test module for the ModelMatcher's fuzzy search functionality. Let's create this test module:",
|
|
"type": "text"
|
|
}
|
|
],
|
|
"tool_results": [],
|
|
"tool_uses": []
|
|
}
|
|
],
|
|
"model": {
|
|
"model": "claude-3-7-sonnet-latest",
|
|
"provider": "zed.dev"
|
|
},
|
|
"profile": "Write",
|
|
"request_token_usage": [
|
|
{
|
|
"cache_creation_input_tokens": 9581,
|
|
"input_tokens": 4,
|
|
"output_tokens": 5
|
|
},
|
|
{
|
|
"cache_creation_input_tokens": 204,
|
|
"cache_read_input_tokens": 9581,
|
|
"input_tokens": 6,
|
|
"output_tokens": 5
|
|
},
|
|
{
|
|
"cache_creation_input_tokens": 104,
|
|
"cache_read_input_tokens": 9785,
|
|
"input_tokens": 6,
|
|
"output_tokens": 5
|
|
},
|
|
{
|
|
"cache_creation_input_tokens": 239,
|
|
"cache_read_input_tokens": 9889,
|
|
"input_tokens": 6,
|
|
"output_tokens": 5
|
|
},
|
|
{
|
|
"cache_creation_input_tokens": 569,
|
|
"cache_read_input_tokens": 10128,
|
|
"input_tokens": 5,
|
|
"output_tokens": 5
|
|
},
|
|
{
|
|
"cache_creation_input_tokens": 87,
|
|
"cache_read_input_tokens": 10697,
|
|
"input_tokens": 5,
|
|
"output_tokens": 2
|
|
},
|
|
{
|
|
"cache_creation_input_tokens": 7355,
|
|
"cache_read_input_tokens": 10784,
|
|
"input_tokens": 5,
|
|
"output_tokens": 3
|
|
}
|
|
],
|
|
"summary": "Fuzzy Search Testing Language Model Selector",
|
|
"updated_at": "2025-05-08T18:20:34.205405751Z",
|
|
"version": "0.2.0"
|
|
}
|