fix: REPL display, /compact panic, identity leak, DeepSeek reasoning, thinking blocks

Five interrelated fixes from parallel Hephaestus sessions:

1. fix(repl): display assistant text after spinner (#2981, #2982, #2937)
   - Added final_assistant_text() call after run_turn spinner completes
   - REPL now shows response text like run_prompt_json does

2. fix(compact): handle Thinking content blocks (#2985)
   - Added ContentBlock::Thinking variant throughout compact summarizer
   - Prevents panic when /compact encounters thinking blocks

3. fix(prompt): provider-aware model identity (#2822)
   - New ModelFamilyIdentity enum (Claude vs Generic)
   - Non-Anthropic models no longer say 'I am Claude'
   - model_family_identity_for() detects provider and sets identity

4. fix(openai): preserve DeepSeek reasoning_content (#2821)
   - Stream parser now captures reasoning_content from OpenAI-compat
   - Emits ThinkingDelta/SignatureDelta events for reasoning models
   - Thinking blocks included in conversation history for re-send

5. feat(runtime): Thinking block support across codebase
   - AssistantEvent::Thinking variant in conversation.rs
   - ContentBlock::Thinking in session serialization
   - Thinking-aware compact summarization
   - Tests for thinking block ordering and content

Closes #2981, #2982, #2937, #2985, #2822, #2821
This commit is contained in:
YeonGyu-Kim
2026-05-06 15:32:34 +09:00
parent 553d25ee50
commit 75c08bc982
15 changed files with 1099 additions and 75 deletions

View File

@@ -24,10 +24,11 @@ use std::thread::{self, JoinHandle};
use std::time::{Duration, Instant, UNIX_EPOCH};
use api::{
detect_provider_kind, resolve_startup_auth_source, AnthropicClient, AuthSource,
ContentBlockDelta, InputContentBlock, InputMessage, MessageRequest, MessageResponse,
OutputContentBlock, PromptCache, ProviderClient as ApiProviderClient, ProviderKind,
StreamEvent as ApiStreamEvent, ToolChoice, ToolDefinition, ToolResultContentBlock,
detect_provider_kind, model_family_identity_for, resolve_startup_auth_source, AnthropicClient,
AuthSource, ContentBlockDelta, InputContentBlock, InputMessage, MessageRequest,
MessageResponse, OutputContentBlock, PromptCache, ProviderClient as ApiProviderClient,
ProviderKind, StreamEvent as ApiStreamEvent, ToolChoice, ToolDefinition,
ToolResultContentBlock,
};
use commands::{
@@ -357,8 +358,9 @@ fn run() -> Result<(), Box<dyn std::error::Error>> {
CliAction::PrintSystemPrompt {
cwd,
date,
model,
output_format,
} => print_system_prompt(cwd, date, output_format)?,
} => print_system_prompt(cwd, date, &model, output_format)?,
CliAction::Version { output_format } => print_version(output_format)?,
CliAction::ResumeSession {
session_path,
@@ -498,6 +500,7 @@ enum CliAction {
PrintSystemPrompt {
cwd: PathBuf,
date: String,
model: String,
output_format: CliOutputFormat,
},
Version {
@@ -960,7 +963,7 @@ fn parse_args(args: &[String]) -> Result<CliAction, String> {
}),
}
}
"system-prompt" => parse_system_prompt_args(&rest[1..], output_format),
"system-prompt" => parse_system_prompt_args(&rest[1..], model, output_format),
"acp" => parse_acp_args(&rest[1..], output_format),
"login" | "logout" => Err(removed_auth_surface_error(rest[0].as_str())),
"init" => Ok(CliAction::Init { output_format }),
@@ -1638,6 +1641,7 @@ fn filter_tool_specs(
fn parse_system_prompt_args(
args: &[String],
model: String,
output_format: CliOutputFormat,
) -> Result<CliAction, String> {
let mut cwd = env::current_dir().map_err(|error| error.to_string())?;
@@ -1674,6 +1678,7 @@ fn parse_system_prompt_args(
Ok(CliAction::PrintSystemPrompt {
cwd,
date,
model,
output_format,
})
}
@@ -2614,9 +2619,16 @@ fn print_bootstrap_plan(output_format: CliOutputFormat) -> Result<(), Box<dyn st
fn print_system_prompt(
cwd: PathBuf,
date: String,
model: &str,
output_format: CliOutputFormat,
) -> Result<(), Box<dyn std::error::Error>> {
let sections = load_system_prompt(cwd, date, env::consts::OS, "unknown")?;
let sections = load_system_prompt(
cwd,
date,
env::consts::OS,
"unknown",
model_family_identity_for(model),
)?;
let message = sections.join(
"
@@ -4394,7 +4406,7 @@ impl LiveCli {
allowed_tools: Option<AllowedToolSet>,
permission_mode: PermissionMode,
) -> Result<Self, Box<dyn std::error::Error>> {
let system_prompt = build_system_prompt()?;
let system_prompt = build_system_prompt(&model)?;
let session_state = new_cli_session()?;
let session = create_managed_session_handle(&session_state.session_id)?;
let runtime = build_runtime(
@@ -4530,6 +4542,10 @@ impl LiveCli {
TerminalRenderer::new().color_theme(),
&mut stdout,
)?;
let final_text = final_assistant_text(&summary);
if !final_text.is_empty() {
println!("{final_text}");
}
println!();
if let Some(event) = summary.auto_compaction {
println!(
@@ -7005,6 +7021,7 @@ fn render_export_text(session: &Session) -> String {
for block in &message.blocks {
match block {
ContentBlock::Text { text } => lines.push(text.clone()),
ContentBlock::Thinking { .. } => {}
ContentBlock::ToolUse { id, name, input } => {
lines.push(format!("[tool_use id={id} name={name}] {input}"));
}
@@ -7191,6 +7208,7 @@ fn render_session_markdown(session: &Session, session_id: &str, session_path: &P
lines.push(String::new());
}
}
ContentBlock::Thinking { .. } => {}
ContentBlock::ToolUse { id, name, input } => {
lines.push(format!(
"**Tool call** `{name}` _(id `{}`)_",
@@ -7244,12 +7262,13 @@ fn short_tool_id(id: &str) -> String {
format!("{prefix}")
}
fn build_system_prompt() -> Result<Vec<String>, Box<dyn std::error::Error>> {
fn build_system_prompt(model: &str) -> Result<Vec<String>, Box<dyn std::error::Error>> {
Ok(load_system_prompt(
env::current_dir()?,
DEFAULT_DATE,
env::consts::OS,
"unknown",
model_family_identity_for(model),
)?)
}
@@ -9211,26 +9230,29 @@ fn convert_messages(messages: &[ConversationMessage]) -> Vec<InputMessage> {
let content = message
.blocks
.iter()
.map(|block| match block {
ContentBlock::Text { text } => InputContentBlock::Text { text: text.clone() },
ContentBlock::ToolUse { id, name, input } => InputContentBlock::ToolUse {
.filter_map(|block| match block {
ContentBlock::Text { text } => {
Some(InputContentBlock::Text { text: text.clone() })
}
ContentBlock::Thinking { .. } => None,
ContentBlock::ToolUse { id, name, input } => Some(InputContentBlock::ToolUse {
id: id.clone(),
name: name.clone(),
input: serde_json::from_str(input)
.unwrap_or_else(|_| serde_json::json!({ "raw": input })),
},
}),
ContentBlock::ToolResult {
tool_use_id,
output,
is_error,
..
} => InputContentBlock::ToolResult {
} => Some(InputContentBlock::ToolResult {
tool_use_id: tool_use_id.clone(),
content: vec![ToolResultContentBlock::Text {
text: output.clone(),
}],
is_error: *is_error,
},
}),
})
.collect::<Vec<_>>();
(!content.is_empty()).then(|| InputMessage {
@@ -9628,7 +9650,9 @@ mod tests {
"{rendered}"
);
assert!(
rendered.contains("Detail Input tokens exceed the configured limit of 922000 tokens."),
rendered.contains(
"Detail Input tokens exceed the configured limit of 922000 tokens."
),
"{rendered}"
);
assert!(rendered.contains("Compact /compact"), "{rendered}");
@@ -10264,6 +10288,7 @@ mod tests {
#[test]
fn parses_system_prompt_options() {
// given: system-prompt options for cwd and date
let args = vec![
"system-prompt".to_string(),
"--cwd".to_string(),
@@ -10271,16 +10296,43 @@ mod tests {
"--date".to_string(),
"2026-04-01".to_string(),
];
// when: parsing the direct system-prompt command
let action = parse_args(&args).expect("args should parse");
// then: the action carries prompt options and default model
assert_eq!(
parse_args(&args).expect("args should parse"),
action,
CliAction::PrintSystemPrompt {
cwd: PathBuf::from("/tmp/project"),
date: "2026-04-01".to_string(),
model: DEFAULT_MODEL.to_string(),
output_format: CliOutputFormat::Text,
}
);
}
#[test]
fn parses_global_model_for_system_prompt() {
// given: a global OpenAI-compatible model before system-prompt
let args = vec![
"--model".to_string(),
"openai/gpt-4.1-mini".to_string(),
"system-prompt".to_string(),
];
// when: parsing the CLI arguments
let action = parse_args(&args).expect("args should parse");
// then: the system-prompt action carries the selected model
match action {
CliAction::PrintSystemPrompt { model, .. } => {
assert_eq!(model, "openai/gpt-4.1-mini");
}
other => panic!("expected PrintSystemPrompt, got {other:?}"),
}
}
#[test]
fn removed_login_and_logout_subcommands_error_helpfully() {
let login = parse_args(&["login".to_string()]).expect_err("login should be removed");

View File

@@ -126,6 +126,66 @@ fn compact_flag_streaming_text_only_emits_final_message_text() {
fs::remove_dir_all(&workspace).expect("workspace cleanup should succeed");
}
#[test]
fn text_prompt_mode_prints_final_assistant_text_after_spinner() {
// given a workspace pointed at the mock Anthropic service running the
// streaming_text scenario which only emits a single assistant text block
let runtime = tokio::runtime::Runtime::new().expect("tokio runtime should build");
let server = runtime
.block_on(MockAnthropicService::spawn())
.expect("mock service should start");
let base_url = server.base_url();
let workspace = unique_temp_dir("text-prompt-mode");
let config_home = workspace.join("config-home");
let home = workspace.join("home");
fs::create_dir_all(&workspace).expect("workspace should exist");
fs::create_dir_all(&config_home).expect("config home should exist");
fs::create_dir_all(&home).expect("home should exist");
// when we invoke claw in normal text prompt mode for the streaming text scenario
let prompt = format!("{SCENARIO_PREFIX}streaming_text");
let output = run_claw(
&workspace,
&config_home,
&home,
&base_url,
&[
"--model",
"sonnet",
"--permission-mode",
"read-only",
&prompt,
],
);
// then stdout should contain the final assistant text, not just spinner output
assert!(
output.status.success(),
"text prompt run should succeed\nstdout:\n{}\n\nstderr:\n{}",
String::from_utf8_lossy(&output.stdout),
String::from_utf8_lossy(&output.stderr),
);
let stdout = String::from_utf8(output.stdout).expect("stdout should be utf8");
let plain_stdout = strip_ansi_codes(&stdout);
assert!(
plain_stdout.contains("Mock streaming says hello from the parity harness."),
"text prompt stdout should include the assistant text ({stdout:?})"
);
assert!(
plain_stdout.contains("✔ ✨ Done"),
"text prompt stdout should still include spinner completion ({stdout:?})"
);
assert!(
plain_stdout
.lines()
.any(|line| line == "Mock streaming says hello from the parity harness."),
"text prompt stdout should print the assistant text as its own line ({stdout:?})"
);
fs::remove_dir_all(&workspace).expect("workspace cleanup should succeed");
}
#[test]
fn compact_flag_with_json_output_emits_structured_json() {
let runtime = tokio::runtime::Runtime::new().expect("tokio runtime should build");
@@ -215,3 +275,21 @@ fn unique_temp_dir(label: &str) -> PathBuf {
std::process::id()
))
}
fn strip_ansi_codes(input: &str) -> String {
let mut output = String::with_capacity(input.len());
let mut chars = input.chars().peekable();
while let Some(ch) = chars.next() {
if ch == '\u{1b}' && matches!(chars.peek(), Some('[')) {
chars.next();
while let Some(next) = chars.next() {
if ('@'..='~').contains(&next) {
break;
}
}
continue;
}
output.push(ch);
}
output
}

View File

@@ -0,0 +1,138 @@
use std::fs;
use std::io::Write;
use std::path::PathBuf;
use std::process::{Command, Output, Stdio};
use std::sync::atomic::{AtomicU64, Ordering};
use std::time::{SystemTime, UNIX_EPOCH};
static TEMP_COUNTER: AtomicU64 = AtomicU64::new(0);
#[test]
fn compact_slash_command_in_repl_does_not_start_nested_tokio_runtime() {
// given
let workspace = unique_temp_dir("compact-repl-panic");
let config_home = workspace.join("config-home");
let home = workspace.join("home");
fs::create_dir_all(&workspace).expect("workspace should exist");
fs::create_dir_all(&config_home).expect("config home should exist");
fs::create_dir_all(&home).expect("home should exist");
// when
let output = run_claw_repl(&workspace, &config_home, &home, "/compact\n/exit\n");
// then
assert!(
output.status.success(),
"compact repl run should succeed\nstdout:\n{}\n\nstderr:\n{}",
String::from_utf8_lossy(&output.stdout),
String::from_utf8_lossy(&output.stderr),
);
let stderr = String::from_utf8(output.stderr).expect("stderr should be utf8");
assert!(
!stderr.contains("Cannot start a runtime"),
"stderr must not contain nested runtime panic: {stderr:?}"
);
assert!(
!stderr.contains("panicked at"),
"stderr must not contain panic output: {stderr:?}"
);
let stdout = String::from_utf8(output.stdout).expect("stdout should be utf8");
let plain_stdout = strip_ansi_codes(&stdout);
assert!(
plain_stdout.contains("Compaction skipped")
|| plain_stdout.contains("Result skipped")
|| plain_stdout.contains("Result compacted"),
"stdout should contain compact report output ({stdout:?})"
);
fs::remove_dir_all(&workspace).expect("workspace cleanup should succeed");
}
fn run_claw_repl(
cwd: &std::path::Path,
config_home: &std::path::Path,
home: &std::path::Path,
stdin: &str,
) -> Output {
let mut command = python_pty_command(env!("CARGO_BIN_EXE_claw"));
let mut child = command
.current_dir(cwd)
.env_clear()
.env("ANTHROPIC_API_KEY", "test-compact-repl-key")
.env("CLAW_CONFIG_HOME", config_home)
.env("HOME", home)
.env("NO_COLOR", "1")
.env("PATH", "/usr/bin:/bin")
.stdin(Stdio::piped())
.stdout(Stdio::piped())
.stderr(Stdio::piped())
.spawn()
.expect("claw should launch");
child
.stdin
.as_mut()
.expect("stdin should be piped")
.write_all(stdin.as_bytes())
.expect("stdin should write");
child.wait_with_output().expect("claw should finish")
}
fn python_pty_command(claw: &str) -> Command {
let mut command = Command::new("python3");
command.args([
"-c",
r#"
import os
import pty
import subprocess
import sys
claw = sys.argv[1]
payload = sys.stdin.buffer.read()
master, slave = pty.openpty()
child = subprocess.Popen([claw], stdin=slave, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
os.close(slave)
os.write(master, payload)
stdout, stderr = child.communicate(timeout=30)
os.close(master)
sys.stdout.buffer.write(stdout)
sys.stderr.buffer.write(stderr)
raise SystemExit(child.returncode)
"#,
claw,
]);
command
}
fn unique_temp_dir(label: &str) -> PathBuf {
let millis = SystemTime::now()
.duration_since(UNIX_EPOCH)
.expect("clock should be after epoch")
.as_millis();
let counter = TEMP_COUNTER.fetch_add(1, Ordering::Relaxed);
std::env::temp_dir().join(format!(
"claw-{label}-{}-{millis}-{counter}",
std::process::id()
))
}
fn strip_ansi_codes(input: &str) -> String {
let mut output = String::with_capacity(input.len());
let mut chars = input.chars().peekable();
while let Some(ch) = chars.next() {
if ch == '\u{1b}' && matches!(chars.peek(), Some('[')) {
chars.next();
for next in chars.by_ref() {
if ('@'..='~').contains(&next) {
break;
}
}
continue;
}
output.push(ch);
}
output
}