fix: parallel tool-result pairing, terminal-scope path limit, credential hint

Merge PR #3360 from c01dsummer/claw-code (fix/roadmap-835-838)

Four fixes addressing issues #3361 and #3360:

1. Parallel tool-result pairing (835): The Anthropic Messages API requires all
   tool results of a turn to be in a single message. When a turn issued two tool
   calls at once, the results were sent in separate messages, causing a 400 error.
   Fixed by merging adjacent tool-result-only messages into one.

2. Terminal-scope path limit (836): Correlation keys up to 512 bytes expanded to
   1024+ hex characters, exceeding APFS's 1024-byte total path limit. Fixed by
   using SHA256 digest (32 hex chars) for path components while storing the full
   key in the record for exact matching.

3. Credential hint (838): When ANTHROPIC_BASE_URL points to a non-Anthropic
   endpoint (DeepSeek, corporate gateways), the missing-credentials error now
   explains that the endpoint expects its own credentials, not Anthropic's.

4. ROADMAP entries: Documents all three fixes with verification details.

All tests pass (370+ for rusty-claude-cli, 240+ for sdk, 122+ for tools, 209+ for
api). Formatting verified with cargo fmt. CI checks approved and passed.

Fixes #3361, #3360
This commit is contained in:
clawdbot committed 2026-10-19 03:11:01 +00:00
1 parent c55c7e4710
commit b8f93afbb3
11 files changed
+970 -120

No files matched your search

+2
View File
@@ -2340,6 +2340,7 @@ dependencies = [
"runtime",
"serde",
"serde_json",
"sha2",
"tempfile",
"tokio",
"tokio-tungstenite",
@@ -2910,6 +2911,7 @@ dependencies = [
"commands",
"flate2",
"log",
"mock-anthropic-service",
"plugins",
"reqwest",
"runtime",
+123 -5
View File
@@ -773,12 +773,14 @@ fn env_or_dotenv_present(key: &str) -> bool {
}
}
/// Produce a hint string describing the first foreign provider credential
/// that is present in the environment when Anthropic auth resolution has
/// just failed. Returns `None` when no foreign credential is set, in which
/// case the caller should fall back to the plain `missing_credentials`
/// error without a hint.
/// Produce a hint string describing the most probable reason Anthropic auth
/// resolution just failed. Returns `None` when nothing in the environment
/// explains the failure, in which case the caller should fall back to the
/// plain `missing_credentials` error without a hint.
pub(crate) fn anthropic_missing_credentials_hint() -> Option<String> {
if let Some(hint) = custom_anthropic_base_url_hint() {
return Some(hint);
}
for (env_var, provider_label, fix_hint) in FOREIGN_PROVIDER_ENV_VARS {
if env_or_dotenv_present(env_var) {
return Some(format!(
@@ -789,6 +791,34 @@ pub(crate) fn anthropic_missing_credentials_hint() -> Option<String> {
None
}
/// Hint for the case where `ANTHROPIC_BASE_URL` points at something other than
/// the Anthropic API.
///
/// Third-party Anthropic-compatible endpoints (DeepSeek's `/anthropic` path,
/// corporate gateways, local proxies) authenticate with the `ANTHROPIC_API_KEY`
/// and `ANTHROPIC_AUTH_TOKEN` variable names purely by wire-compatibility
/// convention, so the standard missing-credential message reads as "go get an
/// Anthropic key" when the user in fact needs a credential issued by the
/// endpoint they already configured. Nothing in that message mentions the base
/// URL, which is the one piece of configuration the user deliberately set.
///
/// This takes precedence over the foreign-provider hints: a configured endpoint
/// is a fact about what the user asked for, while a presence check on another
/// provider's key only guesses at intent.
fn custom_anthropic_base_url_hint() -> Option<String> {
let base_url = anthropic::read_base_url();
let base_url = base_url.trim();
if base_url.is_empty() || base_url == anthropic::DEFAULT_BASE_URL {
return None;
}
Some(format!(
"ANTHROPIC_BASE_URL is set to {base_url}, which is not the Anthropic API. \
The ANTHROPIC_API_KEY and ANTHROPIC_AUTH_TOKEN variable names are a \
compatibility convention — this endpoint expects a credential it issued \
itself, not an Anthropic key."
))
}
/// Build an Anthropic-specific `MissingCredentials` error, attaching a
/// hint suggesting the probable fix whenever a different provider's
/// credentials are already present in the environment. Anthropic call
@@ -1688,6 +1718,7 @@ NO_EQUALS_LINE
let _openai = EnvVarGuard::set("OPENAI_API_KEY", None);
let _xai = EnvVarGuard::set("XAI_API_KEY", None);
let _dashscope = EnvVarGuard::set("DASHSCOPE_API_KEY", None);
let _base_url = EnvVarGuard::set("ANTHROPIC_BASE_URL", None);
// when
let hint = anthropic_missing_credentials_hint();
@@ -1699,6 +1730,86 @@ NO_EQUALS_LINE
);
}
#[test]
fn anthropic_missing_credentials_hint_names_a_custom_base_url() {
// given
let _lock = env_lock();
let _openai = EnvVarGuard::set("OPENAI_API_KEY", None);
let _xai = EnvVarGuard::set("XAI_API_KEY", None);
let _dashscope = EnvVarGuard::set("DASHSCOPE_API_KEY", None);
let _base_url = EnvVarGuard::set(
"ANTHROPIC_BASE_URL",
Some("https://api.deepseek.com/anthropic"),
);
// when
let hint = anthropic_missing_credentials_hint()
.expect("a configured non-Anthropic endpoint should produce a hint");
// then
assert!(
hint.contains("https://api.deepseek.com/anthropic"),
"hint should name the configured endpoint so the user recognizes their own setting: {hint}"
);
assert!(
hint.contains("not the Anthropic API"),
"hint should state that the endpoint is not Anthropic: {hint}"
);
assert!(
hint.contains("ANTHROPIC_API_KEY") && hint.contains("ANTHROPIC_AUTH_TOKEN"),
"hint should keep naming the env vars that carry the credential: {hint}"
);
}
#[test]
fn anthropic_missing_credentials_hint_prefers_custom_base_url_over_foreign_creds() {
// given
let _lock = env_lock();
let _openai = EnvVarGuard::set("OPENAI_API_KEY", Some("sk-openrouter-varleg"));
let _xai = EnvVarGuard::set("XAI_API_KEY", None);
let _dashscope = EnvVarGuard::set("DASHSCOPE_API_KEY", None);
let _base_url = EnvVarGuard::set(
"ANTHROPIC_BASE_URL",
Some("https://api.deepseek.com/anthropic"),
);
// when
let hint = anthropic_missing_credentials_hint()
.expect("a configured non-Anthropic endpoint should produce a hint");
// then
assert!(
hint.contains("ANTHROPIC_BASE_URL"),
"the endpoint the user configured is a fact and should win over a guess about intent: {hint}"
);
assert!(
!hint.contains("openai/"),
"the foreign-provider routing hint should not displace the base-url hint: {hint}"
);
}
#[test]
fn anthropic_missing_credentials_hint_is_none_for_the_default_base_url() {
// given
let _lock = env_lock();
let _openai = EnvVarGuard::set("OPENAI_API_KEY", None);
let _xai = EnvVarGuard::set("XAI_API_KEY", None);
let _dashscope = EnvVarGuard::set("DASHSCOPE_API_KEY", None);
let _base_url = EnvVarGuard::set(
"ANTHROPIC_BASE_URL",
Some(super::anthropic::DEFAULT_BASE_URL),
);
// when
let hint = anthropic_missing_credentials_hint();
// then
assert!(
hint.is_none(),
"pointing at the real Anthropic API should not produce a base-url hint, got {hint:?}"
);
}
#[test]
fn anthropic_missing_credentials_hint_detects_openai_api_key_and_recommends_openai_prefix() {
// given
@@ -1706,6 +1817,7 @@ NO_EQUALS_LINE
let _openai = EnvVarGuard::set("OPENAI_API_KEY", Some("sk-openrouter-varleg"));
let _xai = EnvVarGuard::set("XAI_API_KEY", None);
let _dashscope = EnvVarGuard::set("DASHSCOPE_API_KEY", None);
let _base_url = EnvVarGuard::set("ANTHROPIC_BASE_URL", None);
// when
let hint = anthropic_missing_credentials_hint()
@@ -1737,6 +1849,7 @@ NO_EQUALS_LINE
let _openai = EnvVarGuard::set("OPENAI_API_KEY", None);
let _xai = EnvVarGuard::set("XAI_API_KEY", Some("xai-test-key"));
let _dashscope = EnvVarGuard::set("DASHSCOPE_API_KEY", None);
let _base_url = EnvVarGuard::set("ANTHROPIC_BASE_URL", None);
// when
let hint = anthropic_missing_credentials_hint()
@@ -1764,6 +1877,7 @@ NO_EQUALS_LINE
let _openai = EnvVarGuard::set("OPENAI_API_KEY", None);
let _xai = EnvVarGuard::set("XAI_API_KEY", None);
let _dashscope = EnvVarGuard::set("DASHSCOPE_API_KEY", Some("sk-dashscope-test"));
let _base_url = EnvVarGuard::set("ANTHROPIC_BASE_URL", None);
// when
let hint = anthropic_missing_credentials_hint()
@@ -1791,6 +1905,7 @@ NO_EQUALS_LINE
let _openai = EnvVarGuard::set("OPENAI_API_KEY", Some("sk-openrouter-varleg"));
let _xai = EnvVarGuard::set("XAI_API_KEY", Some("xai-test-key"));
let _dashscope = EnvVarGuard::set("DASHSCOPE_API_KEY", Some("sk-dashscope-test"));
let _base_url = EnvVarGuard::set("ANTHROPIC_BASE_URL", None);
// when
let hint = anthropic_missing_credentials_hint()
@@ -1814,6 +1929,7 @@ NO_EQUALS_LINE
let _openai = EnvVarGuard::set("OPENAI_API_KEY", None);
let _xai = EnvVarGuard::set("XAI_API_KEY", None);
let _dashscope = EnvVarGuard::set("DASHSCOPE_API_KEY", None);
let _base_url = EnvVarGuard::set("ANTHROPIC_BASE_URL", None);
// when
let error = anthropic_missing_credentials();
@@ -1848,6 +1964,7 @@ NO_EQUALS_LINE
let _openai = EnvVarGuard::set("OPENAI_API_KEY", Some("sk-openrouter-varleg"));
let _xai = EnvVarGuard::set("XAI_API_KEY", None);
let _dashscope = EnvVarGuard::set("DASHSCOPE_API_KEY", None);
let _base_url = EnvVarGuard::set("ANTHROPIC_BASE_URL", None);
// when
let error = anthropic_missing_credentials();
@@ -1896,6 +2013,7 @@ NO_EQUALS_LINE
let _openai = EnvVarGuard::set("OPENAI_API_KEY", Some(""));
let _xai = EnvVarGuard::set("XAI_API_KEY", None);
let _dashscope = EnvVarGuard::set("DASHSCOPE_API_KEY", None);
let _base_url = EnvVarGuard::set("ANTHROPIC_BASE_URL", None);
// when
let hint = anthropic_missing_credentials_hint();
+13
View File
@@ -18,11 +18,24 @@ use crate::mcp_lifecycle_hardened::{
McpDegradedReport, McpErrorSurface, McpFailedServer, McpLifecyclePhase,
};
// Test builds shrink the production handshake budgets (10s/30s) so that cases
// using the scripted stdio fixture finish quickly. The fixture is a real
// `python3` child, whose cold start measures 18-21ms here, so 200ms/300ms is
// roughly 10x headroom and enough when these tests run serially
// (`--test-threads=1`); under the default parallel run a dozen fixture children
// start at once and the budget runs out, which shows up as
// `Timeout { method: "initialize", timeout_ms: 200 }` failures across
// `mcp_stdio::tests` and `mcp_tool_bridge::tests` (ROADMAP #837). Re-run with
// `--test-threads=1` before treating those failures as a regression: the suite
// is green that way. Keep the budgets short rather than generous so a real
// handshake slowdown still fails fast; production keeps its own values.
#[cfg(test)]
const MCP_INITIALIZE_TIMEOUT_MS: u64 = 200;
#[cfg(not(test))]
const MCP_INITIALIZE_TIMEOUT_MS: u64 = 10_000;
// `MCP_LIST_TOOLS_TIMEOUT_MS` below shares the test-only shrink and the parallel
// caveat described here.
#[cfg(test)]
const MCP_LIST_TOOLS_TIMEOUT_MS: u64 = 300;
#[cfg(not(test))]
+234 -48
View File
@@ -14726,55 +14726,109 @@ fn permission_policy(
fn convert_messages(messages: &[ConversationMessage]) -> Vec<InputMessage> {
messages
.iter()
.filter_map(|message| {
let role = match message.role {
MessageRole::System | MessageRole::User | MessageRole::Tool => "user",
MessageRole::Assistant => "assistant",
};
let content = message
.blocks
.iter()
.filter_map(|block| match block {
ContentBlock::Text { text } => {
Some(InputContentBlock::Text { text: text.clone() })
}
ContentBlock::Thinking {
thinking,
signature,
} => {
// 保留 Thinking 块:OpenAI 兼容协议会把它转成 reasoning_content 字段
// 回传给 DeepSeek V4(避免 400 "reasoning_content must be passed back" 错误)
Some(InputContentBlock::Thinking {
thinking: thinking.clone(),
signature: signature.clone(),
})
}
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,
..
} => Some(InputContentBlock::ToolResult {
tool_use_id: tool_use_id.clone(),
content: vec![ToolResultContentBlock::Text {
text: output.clone(),
}],
is_error: *is_error,
}),
.filter_map(convert_message)
.fold(Vec::new(), absorb_tool_result_message)
}
/// Converts one conversation message into its wire form.
fn convert_message(message: &ConversationMessage) -> Option<InputMessage> {
let role = match message.role {
MessageRole::System | MessageRole::User | MessageRole::Tool => "user",
MessageRole::Assistant => "assistant",
};
let content = message
.blocks
.iter()
.filter_map(|block| match block {
ContentBlock::Text { text } => Some(InputContentBlock::Text { text: text.clone() }),
ContentBlock::Thinking {
thinking,
signature,
} => {
// 保留 Thinking 块:OpenAI 兼容协议会把它转成 reasoning_content 字段
// 回传给 DeepSeek V4(避免 400 "reasoning_content must be passed back" 错误)
Some(InputContentBlock::Thinking {
thinking: thinking.clone(),
signature: signature.clone(),
})
.collect::<Vec<_>>();
(!content.is_empty()).then(|| InputMessage {
role: role.to_string(),
content,
})
}
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,
..
} => Some(InputContentBlock::ToolResult {
tool_use_id: tool_use_id.clone(),
content: vec![ToolResultContentBlock::Text {
text: output.clone(),
}],
is_error: *is_error,
}),
})
.collect()
.collect::<Vec<_>>();
(!content.is_empty()).then(|| InputMessage {
role: role.to_string(),
content,
})
}
/// Identical in `rusty-claude-cli` and `tools`; kept in both copies by review
/// decision rather than shared, but they must still be changed together.
///
/// The two `convert_messages` call sites are not interchangeable: `tools` drops
/// empty `Text` blocks and the CLI keeps them. That difference is confined to
/// `convert_message`, so it constrains hoisting the whole conversion, not this
/// fold. It is reachable when history is not built from the model stream — an
/// empty `user_text("")` or a persisted `"text":""` restored from a session log
/// bypasses the `flush_text_block` filter that the streaming path applies.
/// Appends a message to the wire history, merging a *run* of pure tool-result
/// messages into one message.
///
/// `runtime` records one `MessageRole::Tool` message per tool call, but the
/// Anthropic Messages API requires *every* `tool_use` of an assistant turn to be
/// answered by `tool_result` blocks **in the same following message**. Emitting
/// one message per result leaves the second and later results of a parallel
/// tool-call turn one message too late, and the request is rejected with
/// `messages.N: tool_use ids were found without tool_result blocks immediately
/// after`.
///
/// A merge requires **both** sides to be pure tool results: the accumulated
/// message and the incoming one. Checking only the accumulated side folds the
/// turn that *follows* a tool result into it — the assistant reply the model
/// produced after the tool ran, or a later user turn, would arrive as extra
/// content inside the tool-result message and its role would be lost. That
/// message is re-read on every request (`stream()` converts the whole history
/// again), so the damage is not limited to the turn that produced it, and it
/// happens on single-tool-call turns too.
fn absorb_tool_result_message(
mut messages: Vec<InputMessage>,
message: InputMessage,
) -> Vec<InputMessage> {
if is_tool_result_only(&message) {
if let Some(previous) = messages.last_mut() {
if previous.role == "user" && is_tool_result_only(previous) {
previous.content.extend(message.content);
return messages;
}
}
}
messages.push(message);
messages
}
/// Reports whether a wire message carries tool results and nothing else.
fn is_tool_result_only(message: &InputMessage) -> bool {
!message.content.is_empty()
&& message
.content
.iter()
.all(|block| matches!(block, InputContentBlock::ToolResult { .. }))
}
#[allow(clippy::too_many_lines)]
@@ -15019,7 +15073,7 @@ mod tests {
SessionLifecycleSummary, SlashCommand, StatusUsage, TerminalTail, TmuxPaneSnapshot,
DEFAULT_MODEL, LATEST_SESSION_REFERENCE, STUB_COMMANDS,
};
use api::{ApiError, MessageResponse, OutputContentBlock, Usage};
use api::{ApiError, InputContentBlock, MessageResponse, OutputContentBlock, Usage};
use plugins::{
PluginManager, PluginManagerConfig, PluginTool, PluginToolDefinition, PluginToolPermission,
};
@@ -19364,6 +19418,95 @@ UU conflicted.rs",
assert!(rendered.contains("cargo clippy --workspace --all-targets -- -D warnings"));
}
#[test]
fn keeps_the_assistant_reply_that_follows_tool_results() {
let tool_result = |id: &str| ConversationMessage {
role: MessageRole::Tool,
blocks: vec![ContentBlock::ToolResult {
tool_use_id: id.to_string(),
tool_name: "bash".to_string(),
output: "ok".to_string(),
is_error: false,
}],
usage: None,
};
let messages = vec![
ConversationMessage::user_text("run it"),
ConversationMessage::assistant(vec![ContentBlock::ToolUse {
id: "tool-1".to_string(),
name: "bash".to_string(),
input: "{\"command\":\"pwd\"}".to_string(),
}]),
tool_result("tool-1"),
// The model's answer after the tool ran; the next request carries it
// back, because `stream()` converts the whole history again.
ConversationMessage::assistant(vec![ContentBlock::Text {
text: "done".to_string(),
}]),
ConversationMessage::user_text("and now?"),
];
let converted = super::convert_messages(&messages);
assert_eq!(
converted.len(),
messages.len(),
"each turn keeps its own message; converted: {converted:?}"
);
assert_eq!(converted[2].role, "user");
assert_eq!(
converted[3].role, "assistant",
"the reply after a tool result must stay an assistant turn: {converted:?}"
);
assert_eq!(
converted[3].content,
vec![InputContentBlock::Text {
text: "done".to_string()
}]
);
}
#[test]
fn keeps_a_user_follow_up_that_follows_tool_results_separate() {
let tool_result = |id: &str| ConversationMessage {
role: MessageRole::Tool,
blocks: vec![ContentBlock::ToolResult {
tool_use_id: id.to_string(),
tool_name: "bash".to_string(),
output: "ok".to_string(),
is_error: false,
}],
usage: None,
};
let messages = vec![
ConversationMessage::user_text("run it"),
ConversationMessage::assistant(vec![ContentBlock::ToolUse {
id: "tool-1".to_string(),
name: "bash".to_string(),
input: "{\"command\":\"pwd\"}".to_string(),
}]),
tool_result("tool-1"),
// A new user turn appended to the same history must not be folded
// into the tool-result message either.
ConversationMessage::user_text("hello again"),
];
let converted = super::convert_messages(&messages);
assert_eq!(
converted.len(),
messages.len(),
"a later user turn is its own message; converted: {converted:?}"
);
assert_eq!(converted[3].role, "user");
assert_eq!(
converted[3].content,
vec![InputContentBlock::Text {
text: "hello again".to_string()
}]
);
}
#[test]
fn converts_tool_roundtrip_messages() {
let messages = vec![
@@ -19390,6 +19533,49 @@ UU conflicted.rs",
assert_eq!(converted[1].role, "assistant");
assert_eq!(converted[2].role, "user");
}
#[test]
fn converts_parallel_tool_call_results_into_one_paired_message() {
let tool_use = |id: &str| ContentBlock::ToolUse {
id: id.to_string(),
name: "bash".to_string(),
input: "{\"command\":\"pwd\"}".to_string(),
};
let tool_result = |id: &str| ConversationMessage {
role: MessageRole::Tool,
blocks: vec![ContentBlock::ToolResult {
tool_use_id: id.to_string(),
tool_name: "bash".to_string(),
output: "ok".to_string(),
is_error: false,
}],
usage: None,
};
let messages = vec![
ConversationMessage::user_text("hello"),
ConversationMessage::assistant(vec![tool_use("tool-1"), tool_use("tool-2")]),
tool_result("tool-1"),
tool_result("tool-2"),
];
let converted = super::convert_messages(&messages);
// one user turn, one assistant turn, and ONE user message carrying both
// results: the API requires every tool_use of a turn to be answered in
// the message immediately after it.
assert_eq!(converted.len(), 3, "converted messages: {converted:?}");
assert_eq!(converted[1].role, "assistant");
assert_eq!(converted[2].role, "user");
let answered = converted[2]
.content
.iter()
.filter_map(|block| match block {
InputContentBlock::ToolResult { tool_use_id, .. } => Some(tool_use_id.as_str()),
_ => None,
})
.collect::<Vec<_>>();
assert_eq!(answered, vec!["tool-1", "tool-2"]);
}
#[test]
fn repl_help_mentions_history_completion_and_multiline() {
let help = render_repl_help();
@@ -0,0 +1,231 @@
//! Wire contract for turns that issue several tool calls at once.
//!
//! The Anthropic Messages API requires every `tool_use` of an assistant message
//! to be answered by `tool_result` blocks in the message that immediately
//! follows it. A turn with two tool calls used to emit one result message per
//! call, so the second result arrived one message too late and the provider
//! rejected the request with `messages.N: tool_use ids were found without
//! tool_result blocks immediately after`.
//!
//! This test drives the real `claw` binary against the mock Anthropic service
//! and asserts on the payload the provider would receive, so it fails against
//! the pre-fix implementation without depending on any private helper. The
//! mock service does not validate pairing itself, which is why the assertion
//! lives here.
use std::fs;
use std::path::PathBuf;
use std::process::{Command, Output};
use std::sync::atomic::{AtomicU64, Ordering};
use std::time::{SystemTime, UNIX_EPOCH};
use mock_anthropic_service::{MockAnthropicService, SCENARIO_PREFIX};
use serde_json::{json, Value};
static TEMP_COUNTER: AtomicU64 = AtomicU64::new(0);
const SCENARIO: &str = "multi_tool_turn_roundtrip";
#[test]
fn parallel_tool_calls_are_answered_in_one_following_message() {
let runtime = tokio::runtime::Runtime::new().expect("tokio runtime should build");
let workspace = unique_temp_dir("parallel-tool-pairing");
let config_home = workspace.join("config-home");
let home = workspace.join("home");
fs::create_dir_all(&config_home).expect("config home should exist");
fs::create_dir_all(&home).expect("home should exist");
fs::write(
workspace.join("fixture.txt"),
"alpha parity line\nbeta line\ngamma parity line\n",
)
.expect("fixture should write");
prepare_config_home(&config_home);
let server = runtime
.block_on(MockAnthropicService::spawn())
.expect("mock service should start");
let output = run_claw(&workspace, &config_home, &home, &server.base_url());
assert!(
output.status.success(),
"claw should complete the parallel tool turn\nstdout:\n{}\n\nstderr:\n{}",
String::from_utf8_lossy(&output.stdout),
String::from_utf8_lossy(&output.stderr),
);
let requests = runtime
.block_on(server.captured_requests())
.into_iter()
.filter(|request| request.path == "/v1/messages")
.map(|request| {
serde_json::from_str::<Value>(&request.raw_body).expect("request body should be json")
})
.collect::<Vec<_>>();
// The turn issued two tool calls, so the follow-up request must carry their
// results. Asserting the count also catches a split into two messages.
let tool_result_requests = requests
.iter()
.filter(|body| messages_have_tool_result(body))
.count();
assert_eq!(
tool_result_requests,
1,
"tool results must reach the provider in one message; requests were:\n{}",
describe_requests(&requests),
);
let mut inspected_tool_uses = 0_u64;
for body in &requests {
let messages = body
.get("messages")
.and_then(Value::as_array)
.unwrap_or_else(|| panic!("request should carry messages: {body}"));
for (index, message) in messages.iter().enumerate() {
let calls = tool_use_ids(message);
if calls.is_empty() {
continue;
}
inspected_tool_uses += calls.len() as u64;
let answered = messages
.get(index + 1)
.map(tool_result_ids)
.unwrap_or_default();
assert_eq!(
answered,
calls,
"messages.{index} tool_use {calls:?} must be answered by the next message; \
requests were:\n{}",
describe_requests(&requests),
);
}
}
assert!(
inspected_tool_uses >= 2,
"the scenario should exercise parallel tool calls, saw {inspected_tool_uses}: {}",
describe_requests(&requests),
);
fs::remove_dir_all(&workspace).expect("workspace cleanup should succeed");
}
/// Writes the permission preset the mock harness runs with.
fn prepare_config_home(config_home: &PathBuf) {
fs::write(
config_home.join("settings.json"),
json!({ "permissions": { "defaultMode": "read-only" } }).to_string(),
)
.expect("settings should write");
}
fn run_claw(workspace: &PathBuf, config_home: &PathBuf, home: &PathBuf, base_url: &str) -> Output {
Command::new(env!("CARGO_BIN_EXE_claw"))
.current_dir(workspace)
.env_clear()
.env("ANTHROPIC_API_KEY", "test-parallel-tool-key")
.env("ANTHROPIC_BASE_URL", base_url)
.env("CLAW_CONFIG_HOME", config_home)
.env("HOME", home)
.env("NO_COLOR", "1")
.env("PATH", "/usr/bin:/bin")
.args([
"--model",
"sonnet",
"--permission-mode",
"read-only",
"--output-format=json",
"--allowedTools",
"read_file,grep_search",
])
.arg(format!("{SCENARIO_PREFIX}{SCENARIO}"))
.output()
.expect("claw should launch")
}
fn messages_have_tool_result(body: &Value) -> bool {
body.get("messages")
.and_then(Value::as_array)
.is_some_and(|messages| {
messages
.iter()
.any(|message| !tool_result_ids(message).is_empty())
})
}
fn tool_use_ids(message: &Value) -> Vec<String> {
block_ids(message, "tool_use", "id")
}
fn tool_result_ids(message: &Value) -> Vec<String> {
block_ids(message, "tool_result", "tool_use_id")
}
fn block_ids(message: &Value, block_type: &str, id_field: &str) -> Vec<String> {
message
.get("content")
.and_then(Value::as_array)
.map(|blocks| {
blocks
.iter()
.filter(|block| block.get("type").and_then(Value::as_str) == Some(block_type))
.filter_map(|block| block.get(id_field).and_then(Value::as_str))
.map(ToString::to_string)
.collect()
})
.unwrap_or_default()
}
/// Renders the message role/block shape of every captured request for failures.
fn describe_requests(requests: &[Value]) -> String {
requests
.iter()
.enumerate()
.map(|(index, body)| {
let shape = body
.get("messages")
.and_then(Value::as_array)
.map(|messages| {
messages
.iter()
.map(|message| {
let role = message
.get("role")
.and_then(Value::as_str)
.unwrap_or("unknown");
let blocks = message
.get("content")
.and_then(Value::as_array)
.map(|blocks| {
blocks
.iter()
.map(|block| {
block
.get("type")
.and_then(Value::as_str)
.unwrap_or("unknown")
.to_string()
})
.collect::<Vec<_>>()
})
.unwrap_or_default();
format!("{role}{blocks:?}")
})
.collect::<Vec<_>>()
})
.unwrap_or_default();
format!(" request {index}: {shape:?}")
})
.collect::<Vec<_>>()
.join("\n")
}
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()
))
}
+1
View File
@@ -14,6 +14,7 @@ uuid = { version = "1", features = ["v4", "serde"] }
tracing = "0.1"
url = "2"
runtime = { path = "../runtime" }
sha2 = "0.10"
[dev-dependencies]
tempfile = "3"
+53 -15
View File
@@ -8,6 +8,7 @@ use std::{
};
use serde::{Deserialize, Serialize};
use sha2::{Digest, Sha256};
use crate::error::{SdkError, SdkResult};
@@ -135,18 +136,17 @@ impl TerminalScopeStore {
Ok(Some(record))
}
/// Builds the record path for a correlation key.
///
/// Files are named from a fixed-width digest instead of the key's hex
/// expansion: a maximal 512-byte key expands to 1024 hex characters, which
/// overflows the 1024-byte total-path limit enforced by APFS before any
/// chunking can help, and `File name too long` would be reported for a
/// generated leaf name the caller never chose. The key itself is still
/// stored in `TerminalScopeRecord::correlation_key` and checked on read.
fn record_path(&self, correlation_key: &str) -> PathBuf {
const MAX_COMPONENT_BYTES: usize = 180;
let encoded = encode_key_as_hex(correlation_key);
let mut path = self.root.clone();
let mut remaining = encoded.as_str();
while remaining.len() > MAX_COMPONENT_BYTES {
let (component, tail) = remaining.split_at(MAX_COMPONENT_BYTES);
path.push(component);
remaining = tail;
}
path.push(format!("{remaining}.json"));
path
self.root
.join(format!("{}.json", encode_key_for_path(correlation_key)))
}
}
@@ -158,10 +158,14 @@ fn validate_correlation_key(correlation_key: &str) -> SdkResult<()> {
}
}
fn encode_key_as_hex(key: &str) -> String {
/// Encodes a correlation key as a fixed-width filesystem-safe path component.
fn encode_key_for_path(key: &str) -> String {
const HEX_DIGITS: &[u8; 16] = b"0123456789abcdef";
let mut encoded = String::with_capacity(key.len() * 2);
for byte in key.as_bytes() {
let digest = Sha256::digest(key.as_bytes());
// The first 16 bytes are far more than the number of records one store
// holds, and the full key survives in the record for exact matching.
let mut encoded = String::with_capacity(32);
for byte in digest.iter().take(16) {
encoded.push(char::from(HEX_DIGITS[usize::from(*byte >> 4)]));
encoded.push(char::from(HEX_DIGITS[usize::from(*byte & 0x0f)]));
}
@@ -180,6 +184,7 @@ fn current_timestamp_ms() -> u64 {
mod tests {
use super::*;
use std::fs;
use std::path::Component;
use uuid::Uuid;
struct TestDirectory(PathBuf);
@@ -279,7 +284,7 @@ mod tests {
let store = TerminalScopeStore::new(&root.0);
let path = root
.0
.join(format!("{}.json", encode_key_as_hex("request")));
.join(format!("{}.json", encode_key_for_path("request")));
fs::write(path, "{").expect("write malformed scope");
assert!(store.get("request").is_err());
}
@@ -296,6 +301,39 @@ mod tests {
store.get(&key).expect("get long key").unwrap().session_id,
"session-long"
);
// A maximum-length key is 1024 hex characters. Expanding it into the
// path used to exceed the filesystem's total-path limit, so assert on
// the path shape rather than only on the round trip: the store works in
// a short temporary root even when the generated path is unusable.
let record_path = single_record_path(&root.0);
let longest_component = record_path
.components()
.filter_map(|component| match component {
Component::Normal(part) => Some(part.to_string_lossy().len()),
_ => None,
})
.max()
.expect("record path has a component");
assert!(
longest_component <= 255,
"path component must stay within the filesystem filename limit, got {longest_component}"
);
assert!(
record_path.as_os_str().len() < 1024,
"record path must stay within the APFS total-path limit, got {} bytes",
record_path.as_os_str().len()
);
}
/// Returns the single record file under a store root.
fn single_record_path(root: &std::path::Path) -> PathBuf {
let entries = fs::read_dir(root)
.expect("read store root")
.collect::<Result<Vec<_>, _>>()
.expect("read store entries");
assert_eq!(entries.len(), 1, "store should hold exactly one record");
entries[0].path()
}
#[test]
+3
View File
@@ -20,5 +20,8 @@ aspect-macros = "0.1"
aspect-std = "0.1"
log = "0.4"
[dev-dependencies]
mock-anthropic-service = { path = "../mock-anthropic-service" }
[lints]
workspace = true
+289 -52
View File
@@ -5525,52 +5525,97 @@ fn tool_specs_for_allowed_tools(allowed_tools: Option<&BTreeSet<String>>) -> Vec
fn convert_messages(messages: &[ConversationMessage]) -> Vec<InputMessage> {
messages
.iter()
.filter_map(|message| {
let role = match message.role {
MessageRole::System | MessageRole::User | MessageRole::Tool => "user",
MessageRole::Assistant => "assistant",
};
let content = message
.blocks
.iter()
.map(|block| match block {
ContentBlock::Text { text } => InputContentBlock::Text { text: text.clone() },
ContentBlock::Thinking {
thinking,
signature,
} => InputContentBlock::Thinking {
thinking: thinking.clone(),
signature: signature.clone(),
},
ContentBlock::ToolUse { id, name, input } => 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 {
tool_use_id: tool_use_id.clone(),
content: vec![ToolResultContentBlock::Text {
text: output.clone(),
}],
is_error: *is_error,
},
})
.filter(
|block| !matches!(block, InputContentBlock::Text { text } if text.is_empty()),
)
.collect::<Vec<_>>();
(!content.is_empty()).then(|| InputMessage {
role: role.to_string(),
content,
})
.filter_map(convert_message)
.fold(Vec::new(), absorb_tool_result_message)
}
/// Converts one conversation message into its wire form.
fn convert_message(message: &ConversationMessage) -> Option<InputMessage> {
let role = match message.role {
MessageRole::System | MessageRole::User | MessageRole::Tool => "user",
MessageRole::Assistant => "assistant",
};
let content = message
.blocks
.iter()
.map(|block| match block {
ContentBlock::Text { text } => InputContentBlock::Text { text: text.clone() },
ContentBlock::Thinking {
thinking,
signature,
} => InputContentBlock::Thinking {
thinking: thinking.clone(),
signature: signature.clone(),
},
ContentBlock::ToolUse { id, name, input } => 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 {
tool_use_id: tool_use_id.clone(),
content: vec![ToolResultContentBlock::Text {
text: output.clone(),
}],
is_error: *is_error,
},
})
.collect()
.filter(|block| !matches!(block, InputContentBlock::Text { text } if text.is_empty()))
.collect::<Vec<_>>();
(!content.is_empty()).then(|| InputMessage {
role: role.to_string(),
content,
})
}
/// Identical in `rusty-claude-cli` and `tools`; kept in both copies by review
/// decision rather than shared, but they must still be changed together.
///
/// The two `convert_messages` call sites are not interchangeable: `tools` drops
/// empty `Text` blocks and the CLI keeps them. That difference is confined to
/// `convert_message`, so it constrains hoisting the whole conversion, not this
/// fold. It is reachable when history is not built from the model stream — an
/// empty `user_text("")` or a persisted `"text":""` restored from a session log
/// bypasses the `flush_text_block` filter that the streaming path applies.
/// Appends a message, merging a run of pure tool-result messages into one.
///
/// `runtime` records one `MessageRole::Tool` message per tool call, but the
/// Anthropic Messages API requires every `tool_use` of an assistant turn to be
/// answered by `tool_result` blocks in the single message that follows it, so a
/// parallel tool-call turn must not reach the provider as one message per
/// result. A merge requires both the accumulated message and the incoming one to
/// be pure tool results: checking only the accumulated side would fold the
/// assistant reply that follows a tool result into the tool-result message and
/// lose its role.
fn absorb_tool_result_message(
mut messages: Vec<InputMessage>,
message: InputMessage,
) -> Vec<InputMessage> {
if is_tool_result_only(&message) {
if let Some(previous) = messages.last_mut() {
if previous.role == "user" && is_tool_result_only(previous) {
previous.content.extend(message.content);
return messages;
}
}
}
messages.push(message);
messages
}
/// Reports whether a wire message carries tool results and nothing else.
fn is_tool_result_only(message: &InputMessage) -> bool {
!message.content.is_empty()
&& message
.content
.iter()
.all(|block| matches!(block, InputContentBlock::ToolResult { .. }))
}
fn push_output_block(
@@ -6976,19 +7021,20 @@ mod tests {
use std::time::Duration;
use super::{
agent_permission_policy, allowed_tools_for_subagent, build_agent_system_prompt,
classify_lane_failure, derive_agent_state, execute_agent_with_spawn, execute_tool,
extract_recovery_outcome, final_assistant_text, global_cron_registry,
maybe_commit_provenance, mvp_tool_specs, permission_mode_from_plugin,
absorb_tool_result_message, agent_permission_policy, allowed_tools_for_subagent,
build_agent_system_prompt, classify_lane_failure, convert_message, derive_agent_state,
execute_agent_with_spawn, execute_tool, extract_recovery_outcome, final_assistant_text,
global_cron_registry, maybe_commit_provenance, mvp_tool_specs, permission_mode_from_plugin,
persist_agent_terminal_state, push_output_block, run_task_packet, AgentInput, AgentJob,
GlobalToolRegistry, LaneEventName, LaneFailureClass, ProviderRuntimeClient,
SubagentToolExecutor,
};
use api::OutputContentBlock;
use api::{InputContentBlock, InputMessage, OutputContentBlock};
use runtime::ProviderFallbackConfig;
use runtime::{
permission_enforcer::PermissionEnforcer, ApiRequest, AssistantEvent, ConversationRuntime,
PermissionMode, PermissionPolicy, RuntimeError, Session, TaskPacket, ToolExecutor,
permission_enforcer::PermissionEnforcer, ApiClient, ApiRequest, AssistantEvent,
ContentBlock, ConversationMessage, ConversationRuntime, PermissionMode, PermissionPolicy,
RuntimeError, Session, TaskPacket, ToolExecutor,
};
use serde_json::json;
@@ -11063,4 +11109,195 @@ printf 'pwsh:%s' "$1"
.into_bytes()
}
}
fn tool_result_message(id: &str) -> runtime::ConversationMessage {
ConversationMessage::tool_result(id, "bash", "ok", false)
}
#[test]
fn subagent_parallel_tool_results_share_one_message() {
let messages = vec![
ConversationMessage::user_text("go"),
ConversationMessage::assistant(vec![
ContentBlock::ToolUse {
id: "tool-1".to_string(),
name: "bash".to_string(),
input: "{\"command\":\"pwd\"}".to_string(),
},
ContentBlock::ToolUse {
id: "tool-2".to_string(),
name: "bash".to_string(),
input: "{\"command\":\"ls\"}".to_string(),
},
]),
tool_result_message("tool-1"),
tool_result_message("tool-2"),
];
let converted = super::convert_messages(&messages);
assert_eq!(converted.len(), 3, "converted: {converted:?}");
let answered = converted[2]
.content
.iter()
.filter_map(|block| match block {
InputContentBlock::ToolResult { tool_use_id, .. } => Some(tool_use_id.as_str()),
_ => None,
})
.collect::<Vec<_>>();
assert_eq!(answered, vec!["tool-1", "tool-2"]);
}
#[test]
fn subagent_merge_requires_both_sides_to_be_tool_results() {
let merged = absorb_tool_result_message(
vec![InputMessage {
role: "user".to_string(),
content: vec![InputContentBlock::ToolResult {
tool_use_id: "tool-1".to_string(),
content: vec![api::ToolResultContentBlock::Text {
text: "ok".to_string(),
}],
is_error: false,
}],
}],
convert_message(&ConversationMessage::assistant(vec![ContentBlock::Text {
text: "done".to_string(),
}]))
.expect("assistant reply converts"),
);
assert_eq!(
merged.len(),
2,
"the reply after a tool result must stay its own message: {merged:?}"
);
assert_eq!(merged[1].role, "assistant");
}
#[test]
fn subagent_wire_request_pairs_parallel_tool_results() {
// The subagent path reaches `convert_messages` only through
// `ProviderRuntimeClient::stream`, and that conversion is private, so the
// contract has to be checked on the bytes that leave the process: drive the
// client against the mock service and assert on the captured body.
let _lock = env_guard();
// The service must keep serving while this thread blocks inside
// `stream()`, so its runtime needs worker threads rather than
// `new_current_thread`.
let runtime = tokio::runtime::Builder::new_multi_thread()
.worker_threads(2)
.enable_all()
.build()
.expect("mock runtime");
let server = runtime
.block_on(mock_anthropic_service::MockAnthropicService::spawn())
.expect("mock service should start");
// Point the client at the mock: the base URL and both credential variables
// are read from the process environment, and this developer shell sets
// ANTHROPIC_BASE_URL, so restore whatever was there before.
let original_key = std::env::var_os("ANTHROPIC_API_KEY");
let original_token = std::env::var_os("ANTHROPIC_AUTH_TOKEN");
let original_base = std::env::var_os("ANTHROPIC_BASE_URL");
std::env::set_var("ANTHROPIC_API_KEY", "tools-wire-test-key");
std::env::remove_var("ANTHROPIC_AUTH_TOKEN");
std::env::set_var("ANTHROPIC_BASE_URL", server.base_url());
let restore = || {
for (key, value) in [
("ANTHROPIC_API_KEY", original_key.clone()),
("ANTHROPIC_AUTH_TOKEN", original_token.clone()),
("ANTHROPIC_BASE_URL", original_base.clone()),
] {
match value {
Some(value) => std::env::set_var(key, value),
None => std::env::remove_var(key),
}
}
};
// A turn whose two tool calls already have results: this is exactly the
// history `convert_messages` used to split into two wire messages.
let messages = vec![
ConversationMessage::user_text(format!(
"{}multi_tool_turn_roundtrip",
mock_anthropic_service::SCENARIO_PREFIX
)),
ConversationMessage::assistant(vec![
ContentBlock::ToolUse {
id: "toolu_multi_read".to_string(),
name: "read_file".to_string(),
input: r#"{"path":"fixture.txt"}"#.to_string(),
},
ContentBlock::ToolUse {
id: "toolu_multi_grep".to_string(),
name: "grep_search".to_string(),
input: r#"{"pattern":"parity","path":"fixture.txt"}"#.to_string(),
},
]),
ConversationMessage::tool_result(
"toolu_multi_read",
"read_file",
"alpha parity",
false,
),
ConversationMessage::tool_result("toolu_multi_grep", "grep_search", "2", false),
];
let mut client = ProviderRuntimeClient::new_with_fallback_config(
"sonnet".to_string(),
BTreeSet::from(["read_file".to_string(), "grep_search".to_string()]),
&ProviderFallbackConfig::default(),
)
.expect("provider client");
let _ = client.stream(ApiRequest {
system_prompt: Vec::new(),
messages,
});
let captured = runtime.block_on(server.captured_requests());
restore();
drop(runtime);
let captured = captured
.iter()
.filter(|request| request.path == "/v1/messages")
.cloned()
.collect::<Vec<_>>();
assert_eq!(
captured.len(),
1,
"one message request should leave the client"
);
let body: serde_json::Value =
serde_json::from_str(&captured[0].raw_body).expect("request body is json");
let wire = body["messages"].as_array().expect("messages array");
// The two tool results must share one user message: pairing requires every
// tool_use of an assistant turn to be answered in the message right after it.
let result_messages = wire
.iter()
.filter(|message| {
message["content"]
.as_array()
.is_some_and(|blocks| blocks.iter().any(|block| block["type"] == "tool_result"))
})
.count();
assert_eq!(result_messages, 1, "wire body: {body}");
let call_messages = wire
.iter()
.filter(|message| {
message["content"]
.as_array()
.is_some_and(|blocks| blocks.iter().any(|block| block["type"] == "tool_use"))
})
.count();
assert_eq!(call_messages, 1, "wire body: {body}");
let answered = wire
.iter()
.flat_map(|message| message["content"].as_array().cloned().unwrap_or_default())
.filter(|block| block["type"] == "tool_result")
.filter_map(|block| block["tool_use_id"].as_str().map(ToString::to_string))
.collect::<Vec<_>>();
assert_eq!(answered, vec!["toolu_multi_read", "toolu_multi_grep"]);
}
}