agent: Overwrite files more cautiously (#30649)
1. The `edit_file` tool tended to use `create_or_overwrite` a bit too often, leading to corruption of long files. This change replaces the boolean flag with an `EditFileMode` enum, which helps Agent make a more deliberate choice when overwriting files. With this change, the pass rate of the new eval increased from 10% to 100%. 2. eval: Added ability to run eval on top of an existing thread. Threads can now be loaded from JSON files in the `SerializedThread` format, which makes it easy to use real threads as starting points for tests/evals. 3. Don't try to restore tool cards when running in headless or eval mode -- we don't have a window to properly do this. Release Notes: - N/A
This commit is contained in:
Oleksiy Syvokon
GitHub
parent
22f76ac1a7
commit
255d8f7cf8
18 changed files with 425 additions and 37 deletions
|
|
@ -711,9 +711,9 @@ fn print_report(
|
|||
.values()
|
||||
.flat_map(|results| {
|
||||
results.iter().map(|(example, _)| {
|
||||
let absolute_path = example.run_directory.join("last.messages.json");
|
||||
pathdiff::diff_paths(&absolute_path, run_dir)
|
||||
.unwrap_or_else(|| absolute_path.clone())
|
||||
let absolute_path = run_dir.join(example.run_directory.join("last.messages.json"));
|
||||
let cwd = std::env::current_dir().expect("Can't get current dir");
|
||||
pathdiff::diff_paths(&absolute_path, cwd).unwrap_or_else(|| absolute_path.clone())
|
||||
})
|
||||
})
|
||||
.collect::<Vec<_>>();
|
||||
|
|
|
|||
|
|
@ -48,6 +48,7 @@ pub struct ExampleMetadata {
|
|||
pub language_server: Option<LanguageServer>,
|
||||
pub max_assertions: Option<usize>,
|
||||
pub profile_id: AgentProfileId,
|
||||
pub existing_thread_json: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug)]
|
||||
|
|
@ -477,12 +478,16 @@ impl Response {
|
|||
tool_name: &'static str,
|
||||
cx: &mut ExampleContext,
|
||||
) -> Result<&ToolUse> {
|
||||
let result = self.messages.iter().find_map(|msg| {
|
||||
let result = self.find_tool_call(tool_name);
|
||||
cx.assert_some(result, format!("called `{}`", tool_name))
|
||||
}
|
||||
|
||||
pub fn find_tool_call(&self, tool_name: &str) -> Option<&ToolUse> {
|
||||
self.messages.iter().rev().find_map(|msg| {
|
||||
msg.tool_use
|
||||
.iter()
|
||||
.find(|tool_use| tool_use.name == tool_name)
|
||||
});
|
||||
cx.assert_some(result, format!("called `{}`", tool_name))
|
||||
})
|
||||
}
|
||||
|
||||
#[allow(dead_code)]
|
||||
|
|
|
|||
|
|
@ -21,6 +21,7 @@ impl Example for AddArgToTraitMethod {
|
|||
}),
|
||||
max_assertions: None,
|
||||
profile_id: AgentProfileId::default(),
|
||||
existing_thread_json: None,
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -22,6 +22,7 @@ impl Example for CodeBlockCitations {
|
|||
}),
|
||||
max_assertions: None,
|
||||
profile_id: AgentProfileId::default(),
|
||||
existing_thread_json: None,
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
use crate::example::{Example, ExampleContext, ExampleMetadata, JudgeAssertion};
|
||||
use anyhow::Result;
|
||||
use assistant_settings::AgentProfileId;
|
||||
use assistant_tools::EditFileToolInput;
|
||||
use assistant_tools::{EditFileMode, EditFileToolInput};
|
||||
use async_trait::async_trait;
|
||||
|
||||
pub struct CommentTranslation;
|
||||
|
|
@ -16,6 +16,7 @@ impl Example for CommentTranslation {
|
|||
language_server: None,
|
||||
max_assertions: Some(1),
|
||||
profile_id: AgentProfileId::default(),
|
||||
existing_thread_json: None,
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -35,7 +36,7 @@ impl Example for CommentTranslation {
|
|||
for tool_use in thread.tool_uses_for_message(message.id, cx) {
|
||||
if tool_use.name == "edit_file" {
|
||||
let input: EditFileToolInput = serde_json::from_value(tool_use.input)?;
|
||||
if input.create_or_overwrite {
|
||||
if !matches!(input.mode, EditFileMode::Edit) {
|
||||
create_or_overwrite_count += 1;
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -18,6 +18,7 @@ impl Example for FileSearchExample {
|
|||
language_server: None,
|
||||
max_assertions: Some(3),
|
||||
profile_id: AgentProfileId::default(),
|
||||
existing_thread_json: None,
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@ mod add_arg_to_trait_method;
|
|||
mod code_block_citations;
|
||||
mod comment_translation;
|
||||
mod file_search;
|
||||
mod overwrite_file;
|
||||
mod planets;
|
||||
|
||||
pub fn all(examples_dir: &Path) -> Vec<Rc<dyn Example>> {
|
||||
|
|
@ -25,6 +26,7 @@ pub fn all(examples_dir: &Path) -> Vec<Rc<dyn Example>> {
|
|||
Rc::new(code_block_citations::CodeBlockCitations),
|
||||
Rc::new(planets::Planets),
|
||||
Rc::new(comment_translation::CommentTranslation),
|
||||
Rc::new(overwrite_file::FileOverwriteExample),
|
||||
];
|
||||
|
||||
for example_path in list_declarative_examples(examples_dir).unwrap() {
|
||||
|
|
@ -45,6 +47,7 @@ impl DeclarativeExample {
|
|||
pub fn load(example_path: &Path) -> Result<Self> {
|
||||
let name = Self::name_from_path(example_path);
|
||||
let base: ExampleToml = toml::from_str(&fs::read_to_string(&example_path)?)?;
|
||||
let example_dir = example_path.parent().unwrap();
|
||||
|
||||
let language_server = if base.require_lsp {
|
||||
Some(crate::example::LanguageServer {
|
||||
|
|
@ -63,6 +66,14 @@ impl DeclarativeExample {
|
|||
AgentProfileId::default()
|
||||
};
|
||||
|
||||
let existing_thread_json = if let Some(path) = base.existing_thread_path {
|
||||
let content = fs::read_to_string(example_dir.join(&path))
|
||||
.unwrap_or_else(|_| panic!("Failed to read existing thread file: {}", path));
|
||||
Some(content)
|
||||
} else {
|
||||
None
|
||||
};
|
||||
|
||||
let metadata = ExampleMetadata {
|
||||
name,
|
||||
url: base.url,
|
||||
|
|
@ -70,6 +81,7 @@ impl DeclarativeExample {
|
|||
language_server,
|
||||
max_assertions: None,
|
||||
profile_id,
|
||||
existing_thread_json,
|
||||
};
|
||||
|
||||
Ok(DeclarativeExample {
|
||||
|
|
@ -110,6 +122,8 @@ pub struct ExampleToml {
|
|||
pub diff_assertions: BTreeMap<String, String>,
|
||||
#[serde(default)]
|
||||
pub thread_assertions: BTreeMap<String, String>,
|
||||
#[serde(default)]
|
||||
pub existing_thread_path: Option<String>,
|
||||
}
|
||||
|
||||
#[async_trait(?Send)]
|
||||
|
|
|
|||
49
crates/eval/src/examples/overwrite_file.rs
Normal file
49
crates/eval/src/examples/overwrite_file.rs
Normal file
|
|
@ -0,0 +1,49 @@
|
|||
use anyhow::Result;
|
||||
use assistant_settings::AgentProfileId;
|
||||
use assistant_tools::{EditFileMode, EditFileToolInput};
|
||||
use async_trait::async_trait;
|
||||
|
||||
use crate::example::{Example, ExampleContext, ExampleMetadata};
|
||||
|
||||
pub struct FileOverwriteExample;
|
||||
|
||||
/*
|
||||
This eval tests a fix for a destructive behavior of the `edit_file` tool.
|
||||
Previously, it would rewrite existing files too aggressively, which often
|
||||
resulted in content loss.
|
||||
|
||||
Pass rate before the fix: 10%
|
||||
Pass rate after the fix: 100%
|
||||
*/
|
||||
|
||||
#[async_trait(?Send)]
|
||||
impl Example for FileOverwriteExample {
|
||||
fn meta(&self) -> ExampleMetadata {
|
||||
let thread_json = include_str!("threads/overwrite-file.json");
|
||||
|
||||
ExampleMetadata {
|
||||
name: "file_overwrite".to_string(),
|
||||
url: "https://github.com/zed-industries/zed.git".to_string(),
|
||||
revision: "023a60806a8cc82e73bd8d88e63b4b07fc7a0040".to_string(),
|
||||
language_server: None,
|
||||
max_assertions: Some(1),
|
||||
profile_id: AgentProfileId::default(),
|
||||
existing_thread_json: Some(thread_json.to_string()),
|
||||
}
|
||||
}
|
||||
|
||||
async fn conversation(&self, cx: &mut ExampleContext) -> Result<()> {
|
||||
let response = cx.run_turns(1).await?;
|
||||
let file_overwritten = if let Some(tool_use) = response.find_tool_call("edit_file") {
|
||||
let input = tool_use.parse_input::<EditFileToolInput>()?;
|
||||
match input.mode {
|
||||
EditFileMode::Edit => false,
|
||||
EditFileMode::Create | EditFileMode::Overwrite => true,
|
||||
}
|
||||
} else {
|
||||
false
|
||||
};
|
||||
|
||||
cx.assert(!file_overwritten, "File should be edited, not overwritten")
|
||||
}
|
||||
}
|
||||
|
|
@ -18,6 +18,7 @@ impl Example for Planets {
|
|||
language_server: None,
|
||||
max_assertions: None,
|
||||
profile_id: AgentProfileId::default(),
|
||||
existing_thread_json: None,
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
262
crates/eval/src/examples/threads/overwrite-file.json
Normal file
262
crates/eval/src/examples/threads/overwrite-file.json
Normal file
|
|
@ -0,0 +1,262 @@
|
|||
{
|
||||
"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\nworkspace-hack.workspace = true\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"
|
||||
}
|
||||
|
|
@ -1,4 +1,4 @@
|
|||
use agent::{Message, MessageSegment, ThreadStore};
|
||||
use agent::{Message, MessageSegment, SerializedThread, ThreadStore};
|
||||
use anyhow::{Context, Result, anyhow, bail};
|
||||
use assistant_tool::ToolWorkingSet;
|
||||
use client::proto::LspWorkProgress;
|
||||
|
|
@ -312,7 +312,14 @@ impl ExampleInstance {
|
|||
thread_store.update(cx, |thread_store, cx| thread_store.load_profile_by_id(profile_id, cx)).expect("Failed to load profile");
|
||||
|
||||
let thread =
|
||||
thread_store.update(cx, |thread_store, cx| thread_store.create_thread(cx))?;
|
||||
thread_store.update(cx, |thread_store, cx| {
|
||||
if let Some(json) = &meta.existing_thread_json {
|
||||
let serialized = SerializedThread::from_json(json.as_bytes()).expect("Can't read serialized thread");
|
||||
thread_store.create_thread_from_serialized(serialized, cx)
|
||||
} else {
|
||||
thread_store.create_thread(cx)
|
||||
}
|
||||
})?;
|
||||
|
||||
|
||||
thread.update(cx, |thread, _cx| {
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue