Merge pull request #3368 from ultraworkers/release/v0.1.9

release: v0.1.9

CHANGELOG.md

@@ -5,6 +5,19 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.1.9] - 2026-10-29
+
+### Fixed
+
+- Trident compaction no longer leaves orphaned tool_result blocks after superseding a file tool use, which made providers reject auto-compact retries with HTTP 400 (#3367)
+
+## [0.1.8] - 2026-10-23
+
+### Fixed
+
+- Web search error handling: explicit 'Web search unavailable (HTTP N)' error on non-2xx responses instead of junk results (#3365)
+- Web search result filtering: drop links back to search engine host (#3365)
+
 ## [0.1.7] - 2026-10-19
 
 ### Added

rust/Cargo.lock

@@ -93,7 +93,7 @@ checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c"
 
 [[package]]
 name = "api"
-version = "0.1.6"
+version = "0.1.9"
 dependencies = [
  "criterion",
  "reqwest",
@@ -478,7 +478,7 @@ checksum = "c8d4a3bb8b1e0c1050499d1815f5ab16d04f0959b233085fb31653fbfc9d98f9"
 
 [[package]]
 name = "claw-analog"
-version = "0.1.6"
+version = "0.1.9"
 dependencies = [
  "api",
  "clap",
@@ -498,7 +498,7 @@ dependencies = [
 
 [[package]]
 name = "claw-rag-service"
-version = "0.1.6"
+version = "0.1.9"
 dependencies = [
  "axum 0.8.9",
  "blake3",
@@ -531,7 +531,7 @@ checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570"
 
 [[package]]
 name = "commands"
-version = "0.1.6"
+version = "0.1.9"
 dependencies = [
  "plugins",
  "runtime",
@@ -540,7 +540,7 @@ dependencies = [
 
 [[package]]
 name = "compat-harness"
-version = "0.1.6"
+version = "0.1.9"
 dependencies = [
  "commands",
  "runtime",
@@ -1568,7 +1568,7 @@ dependencies = [
 
 [[package]]
 name = "mock-anthropic-service"
-version = "0.1.6"
+version = "0.1.9"
 dependencies = [
  "api",
  "serde_json",
@@ -1761,7 +1761,7 @@ dependencies = [
 
 [[package]]
 name = "plugins"
-version = "0.1.6"
+version = "0.1.9"
 dependencies = [
  "serde",
  "serde_json",
@@ -2136,7 +2136,7 @@ dependencies = [
 
 [[package]]
 name = "runtime"
-version = "0.1.6"
+version = "0.1.9"
 dependencies = [
  "glob",
  "plugins",
@@ -2261,7 +2261,7 @@ checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
 
 [[package]]
 name = "rusty-claude-cli"
-version = "0.1.6"
+version = "0.1.9"
 dependencies = [
  "api",
  "commands",
@@ -2622,7 +2622,7 @@ dependencies = [
 
 [[package]]
 name = "telemetry"
-version = "0.1.6"
+version = "0.1.9"
 dependencies = [
  "serde",
  "serde_json",
@@ -2902,7 +2902,7 @@ dependencies = [
 
 [[package]]
 name = "tools"
-version = "0.1.6"
+version = "0.1.9"
 dependencies = [
  "api",
  "aspect-core",

rust/Cargo.toml

@@ -3,7 +3,7 @@ members = ["crates/*"]
 resolver = "2"
 
 [workspace.package]
-version = "0.1.7"
+version = "0.1.9"
 edition = "2021"
 license = "MIT"
 publish = false

rust/crates/api/tests/client_integration.rs

@@ -82,7 +82,7 @@ async fn send_message_posts_json_and_parses_response() {
     );
     assert_eq!(
         request.headers.get("user-agent").map(String::as_str),
-        Some("claude-code/0.1.7")
+        Some("claude-code/0.1.9")
     );
     assert_eq!(
         request.headers.get("anthropic-beta").map(String::as_str),

rust/crates/runtime/src/trident.rs

@@ -216,6 +216,48 @@ fn stage1_supersede(messages: &[ConversationMessage]) -> (Vec<ConversationMessag
         }
     }
 
+    // A tool result is only meaningful together with the tool use that
+    // produced it. Dropping the tool use while keeping its result leaves an
+    // orphaned `tool_result` block, which providers reject with
+    // "tool_result blocks must be a response to a preceding tool_use".
+    let dropped_tool_use_ids: BTreeSet<&str> = obsolete_indices
+        .iter()
+        .filter_map(|index| messages.get(*index))
+        .flat_map(|message| message.blocks.iter())
+        .filter_map(|block| match block {
+            ContentBlock::ToolUse { id, .. } => Some(id.as_str()),
+            _ => None,
+        })
+        .collect();
+
+    for (index, message) in messages.iter().enumerate() {
+        if obsolete_indices.contains(&index) {
+            continue;
+        }
+        let answers_dropped_tool_use = message.blocks.iter().any(|block| {
+            matches!(
+                block,
+                ContentBlock::ToolResult { tool_use_id, .. }
+                    if dropped_tool_use_ids.contains(tool_use_id.as_str())
+            )
+        });
+        if !answers_dropped_tool_use {
+            continue;
+        }
+        // Keep a message that still carries a surviving tool use: dropping it
+        // would orphan that tool use instead.
+        let keeps_surviving_tool_use = message.blocks.iter().any(|block| {
+            matches!(
+                block,
+                ContentBlock::ToolUse { id, .. }
+                    if !dropped_tool_use_ids.contains(id.as_str())
+            )
+        });
+        if !keeps_surviving_tool_use {
+            obsolete_indices.insert(index);
+        }
+    }
+
     let superseded_count = obsolete_indices.len();
     let kept: Vec<ConversationMessage> = messages
         .iter()
@@ -239,18 +281,11 @@ fn extract_file_operation(block: &ContentBlock) -> Option<(String, FileOp)> {
             };
             Some((path, op_type))
         }
-        ContentBlock::ToolResult {
-            tool_name, output, ..
-        } => {
-            let path = extract_path_from_tool_output(tool_name, output)?;
-            let op_type = match tool_name.as_str() {
-                "read_file" | "Read" => FileOp::Read,
-                "write_file" | "Write" => FileOp::Write,
-                "edit_file" | "Edit" => FileOp::Edit,
-                _ => return None,
-            };
-            Some((path, op_type))
-        }
+        // A tool result is the answer half of a tool use, not an independent
+        // file operation. Counting it as one shifts `last_write` past the
+        // write it belongs to, which makes the newest write look obsolete
+        // and splits its tool-use/tool-result pair.
+        ContentBlock::ToolResult { .. } => None,
         ContentBlock::Text { .. } => None,
         ContentBlock::Thinking { .. } => None,
     }
@@ -732,6 +767,90 @@ mod tests {
         assert_eq!(kept.len(), messages.len());
     }
 
+    #[test]
+    fn stage1_keeps_tool_use_and_result_paired() {
+        // Realistic transcript: the model reads the same file twice and then
+        // rewrites it. Stage 1 must drop the obsolete reads *and* their tool
+        // results, but it must never leave a `tool_result` behind without the
+        // `tool_use` that produced it: providers reject such requests with
+        // "tool_result blocks must be a response to a preceding tool_use".
+        let messages = vec![
+            ConversationMessage::assistant(vec![ContentBlock::ToolUse {
+                id: "1".to_string(),
+                name: "read_file".to_string(),
+                input: r#"{"path":"src/main.rs"}"#.to_string(),
+            }]),
+            ConversationMessage::tool_result(
+                "1",
+                "read_file",
+                r#"{"type":"text","file":{"filePath":"/ws/src/main.rs","content":"old"}}"#,
+                false,
+            ),
+            ConversationMessage::assistant(vec![ContentBlock::ToolUse {
+                id: "2".to_string(),
+                name: "read_file".to_string(),
+                input: r#"{"path":"src/main.rs"}"#.to_string(),
+            }]),
+            ConversationMessage::tool_result(
+                "2",
+                "read_file",
+                r#"{"type":"text","file":{"filePath":"/ws/src/main.rs","content":"old"}}"#,
+                false,
+            ),
+            ConversationMessage::assistant(vec![ContentBlock::ToolUse {
+                id: "3".to_string(),
+                name: "write_file".to_string(),
+                input: r#"{"path":"src/main.rs","content":"new"}"#.to_string(),
+            }]),
+            ConversationMessage::tool_result(
+                "3",
+                "write_file",
+                r#"{"type":"update","filePath":"/ws/src/main.rs","content":"new"}"#,
+                false,
+            ),
+        ];
+
+        let (kept, superseded) = stage1_supersede(&messages);
+        assert!(superseded > 0, "obsolete reads should be superseded");
+
+        let tool_use_ids: BTreeSet<&str> = kept
+            .iter()
+            .flat_map(|message| message.blocks.iter())
+            .filter_map(|block| match block {
+                ContentBlock::ToolUse { id, .. } => Some(id.as_str()),
+                _ => None,
+            })
+            .collect();
+        for message in &kept {
+            for block in &message.blocks {
+                if let ContentBlock::ToolResult { tool_use_id, .. } = block {
+                    assert!(
+                        tool_use_ids.contains(tool_use_id.as_str()),
+                        "orphaned tool_result for tool_use {tool_use_id}"
+                    );
+                }
+            }
+        }
+
+        // The most recent write survives, together with its tool result.
+        let has_tool_use = |id: &str| {
+            kept.iter().any(|message| {
+                message.blocks.iter().any(
+                    |block| matches!(block, ContentBlock::ToolUse { id: tool_use_id, .. } if tool_use_id == id),
+                )
+            })
+        };
+        let has_tool_result = |id: &str| {
+            kept.iter().any(|message| {
+                message.blocks.iter().any(
+                    |block| matches!(block, ContentBlock::ToolResult { tool_use_id, .. } if tool_use_id == id),
+                )
+            })
+        };
+        assert!(has_tool_use("3"), "the newest write must survive");
+        assert!(has_tool_result("3"), "its tool result must survive too");
+    }
+
     #[test]
     fn stage2_collapses_chatty_messages() {
         let mut messages = vec![];

rust/crates/tools/src/lib.rs

@@ -3528,16 +3528,26 @@ fn execute_web_search(input: &WebSearchInput) -> Result<WebSearchOutput, String>
     let client = build_http_client()?;
     let search_url = build_search_url(&input.query)?;
     let response = client
-        .get(search_url)
+        .get(search_url.as_str())
         .send()
         .map_err(|error| error.to_string())?;
 
+    // DuckDuckGo answers its bot challenge with HTTP 202 and a page without
+    // results, so anything but 200 is an unusable results page.
+    let status = response.status();
+    if status != reqwest::StatusCode::OK {
+        return Err(format!(
+            "Web search unavailable (HTTP {}) - the search provider is blocked or unreachable",
+            status.as_u16()
+        ));
+    }
+
     let final_url = response.url().clone();
     let html = response.text().map_err(|error| error.to_string())?;
     let mut hits = extract_search_hits(&html);
 
     if hits.is_empty() && final_url.host_str().is_some() {
-        hits = extract_search_hits_from_generic_links(&html);
+        hits = extract_search_hits_from_generic_links(&html, search_url.host_str());
     }
 
     if let Some(allowed) = input.allowed_domains.as_ref() {
@@ -3760,7 +3770,7 @@ fn extract_search_hits(html: &str) -> Vec<SearchHit> {
     hits
 }
 
-fn extract_search_hits_from_generic_links(html: &str) -> Vec<SearchHit> {
+fn extract_search_hits_from_generic_links(html: &str, search_host: Option<&str>) -> Vec<SearchHit> {
     let mut hits = Vec::new();
     let mut remaining = html;
 
@@ -3791,6 +3801,11 @@ fn extract_search_hits_from_generic_links(html: &str) -> Vec<SearchHit> {
         }
         let decoded_url = decode_duckduckgo_redirect(&url).unwrap_or(url);
         if decoded_url.starts_with("http://") || decoded_url.starts_with("https://") {
+            if is_search_engine_link(&decoded_url, search_host) {
+                remaining = &after_tag[end_anchor_idx + 4..];
+                continue;
+            }
+
             hits.push(SearchHit {
                 title: title.trim().to_string(),
                 url: decoded_url,
@@ -3873,6 +3888,20 @@ fn normalize_domain_filter(domain: &str) -> String {
         .to_ascii_lowercase()
 }
 
+/// A generic-fallback link that points back at DuckDuckGo or at the configured
+/// search host is page chrome (home, settings, challenge), never a result.
+fn is_search_engine_link(url: &str, search_host: Option<&str>) -> bool {
+    let Some(host) = reqwest::Url::parse(url)
+        .ok()
+        .and_then(|parsed| parsed.host_str().map(str::to_ascii_lowercase))
+    else {
+        return false;
+    };
+    host == "duckduckgo.com"
+        || host.ends_with(".duckduckgo.com")
+        || search_host.is_some_and(|search_host| host.eq_ignore_ascii_case(search_host))
+}
+
 fn dedupe_hits(hits: &mut Vec<SearchHit>) {
     let mut seen = BTreeSet::new();
     hits.retain(|hit| seen.insert(hit.url.clone()));
@@ -8273,6 +8302,112 @@ mod tests {
         assert_eq!(content[0]["url"], "https://docs.rs/tokio");
     }
 
+    #[test]
+    fn web_search_returns_error_on_non_2xx_response() {
+        let _guard = env_lock()
+            .lock()
+            .unwrap_or_else(std::sync::PoisonError::into_inner);
+        let server = TestServer::spawn(Arc::new(|request_line: &str| {
+            assert!(request_line.contains("GET /search?q=test"));
+            // Simulate rate-limited/blocked response (HTTP 429)
+            HttpResponse::html(
+                429,
+                "Too Many Requests",
+                "<html><body>\n                  <p>Too many requests. Please try again later.</p>\n                </body></html>",
+            )
+        }));
+
+        std::env::set_var(
+            "CLAWD_WEB_SEARCH_BASE_URL",
+            format!("http://{}/search", server.addr()),
+        );
+        let error = execute_tool("WebSearch", &json!({ "query": "test" }))
+            .expect_err("non-2xx response should fail");
+        std::env::remove_var("CLAWD_WEB_SEARCH_BASE_URL");
+
+        assert!(error.contains("Web search unavailable"));
+        assert!(error.contains("429"));
+    }
+
+    #[test]
+    fn web_search_rejects_duckduckgo_202_challenge_page() {
+        let _guard = env_lock()
+            .lock()
+            .unwrap_or_else(std::sync::PoisonError::into_inner);
+        let server = TestServer::spawn(Arc::new(|request_line: &str| {
+            assert!(request_line.contains("GET /html/?q=challenge "));
+            HttpResponse::html(
+                202,
+                "Accepted",
+                r#"
+                <html><body>
+                  <a href="/html/">DuckDuckGo</a>
+                  <a href="https://duckduckgo.com/">Home</a>
+                  <p>Unfortunately, bots use DuckDuckGo too.</p>
+                </body></html>
+                "#,
+            )
+        }));
+
+        std::env::set_var(
+            "CLAWD_WEB_SEARCH_BASE_URL",
+            format!("http://{}/html/", server.addr()),
+        );
+        let error = execute_tool("WebSearch", &json!({ "query": "challenge" }))
+            .expect_err("a 202 challenge page must not produce results");
+        std::env::remove_var("CLAWD_WEB_SEARCH_BASE_URL");
+
+        assert!(
+            error.contains("Web search unavailable (HTTP 202)"),
+            "{error}"
+        );
+    }
+
+    #[test]
+    fn web_search_generic_fallback_drops_search_engine_links() {
+        let _guard = env_lock()
+            .lock()
+            .unwrap_or_else(std::sync::PoisonError::into_inner);
+        let server = TestServer::spawn(Arc::new(|request_line: &str| {
+            assert!(request_line.contains("GET /search?q=chrome+links "));
+            HttpResponse::html(
+                200,
+                "OK",
+                r#"
+                <html><body>
+                  <a href="/html/">DuckDuckGo</a>
+                  <a href="https://html.duckduckgo.com/html/?q=x">Next page</a>
+                  <a href="https://duckduckgo.com/settings">Settings</a>
+                  <a href="https://docs.rs/serde">Serde Docs</a>
+                  <a href="https://tokio.rs/">Tokio</a>
+                </body></html>
+                "#,
+            )
+        }));
+
+        std::env::set_var(
+            "CLAWD_WEB_SEARCH_BASE_URL",
+            format!("http://{}/search", server.addr()),
+        );
+        let result = execute_tool("WebSearch", &json!({ "query": "chrome links" }))
+            .expect("WebSearch fallback parsing should succeed");
+        std::env::remove_var("CLAWD_WEB_SEARCH_BASE_URL");
+
+        let output: serde_json::Value = serde_json::from_str(&result).expect("valid json");
+        let content = output["results"]
+            .as_array()
+            .expect("results array")
+            .iter()
+            .find_map(|item| item.get("content"))
+            .and_then(serde_json::Value::as_array)
+            .expect("search result block present");
+        let urls: Vec<&str> = content
+            .iter()
+            .map(|hit| hit["url"].as_str().expect("url"))
+            .collect();
+        assert_eq!(urls, ["https://docs.rs/serde", "https://tokio.rs/"]);
+    }
+
     #[test]
     fn pending_tools_preserve_multiple_streaming_tool_calls_by_index() {
         let mut events = Vec::new();