docagent-cli 0.0.41__tar.gz → 0.0.42__tar.gz

{docagent_cli-0.0.41 → docagent_cli-0.0.42}/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## [0.0.42](https://github.com/langchain-ai/docagent/compare/docagent-cli==0.0.41...docagent-cli==0.0.42) (2026-04-10)
+
+### Bug Fixes
+
+* Fix `JSONEncoder` crash caused by `encoding="utf-8"` being incorrectly injected into `json.dumps()` calls instead of `write_text()` during the 0.0.41 encoding fix
+
 ## [0.0.41](https://github.com/langchain-ai/docagent/compare/docagent-cli==0.0.40...docagent-cli==0.0.41) (2026-04-10)
 
 ### Bug Fixes

{docagent_cli-0.0.41 → docagent_cli-0.0.42}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docagent-cli
-Version: 0.0.41
+Version: 0.0.42
 Summary: Terminal interface for Deep Agents - interactive AI agent with file operations, shell access, and sub-agent capabilities.
 Project-URL: Homepage, https://docs.langchain.com/oss/python/docagent/overview
 Project-URL: Documentation, https://reference.langchain.com/python/docagent/

{docagent_cli-0.0.41 → docagent_cli-0.0.42}/docagent_cli/_version.py

@@ -1,6 +1,6 @@
 """Version information and lightweight constants for `docagent-cli`."""
 
-__version__ = "0.0.41"  # x-release-please-version
+__version__ = "0.0.42"  # x-release-please-version
 
 DOCS_URL = "https://docs.langchain.com/oss/python/docagent/cli"
 """URL for `docagent-cli` documentation."""

{docagent_cli-0.0.41 → docagent_cli-0.0.42}/docagent_cli/built_in_skills/skill-creator/eval-viewer/generate_review.py

@@ -24,7 +24,7 @@ import sys
 import time
 import webbrowser
 from functools import partial
-from http.server import HTTPServer, BaseHTTPRequestHandler
+from http.server import BaseHTTPRequestHandler, HTTPServer
 from pathlib import Path
 
 # Files to exclude from output listings
@@ -32,9 +32,32 @@ METADATA_FILES = {"transcript.md", "user_notes.md", "metrics.json"}
 
 # Extensions we render as inline text
 TEXT_EXTENSIONS = {
-    ".txt", ".md", ".json", ".csv", ".py", ".js", ".ts", ".tsx", ".jsx",
-    ".yaml", ".yml", ".xml", ".html", ".css", ".sh", ".rb", ".go", ".rs",
-    ".java", ".c", ".cpp", ".h", ".hpp", ".sql", ".r", ".toml",
+    ".txt",
+    ".md",
+    ".json",
+    ".csv",
+    ".py",
+    ".js",
+    ".ts",
+    ".tsx",
+    ".jsx",
+    ".yaml",
+    ".yml",
+    ".xml",
+    ".html",
+    ".css",
+    ".sh",
+    ".rb",
+    ".go",
+    ".rs",
+    ".java",
+    ".c",
+    ".cpp",
+    ".h",
+    ".hpp",
+    ".sql",
+    ".r",
+    ".toml",
 }
 
 # Extensions we render as inline images
@@ -88,7 +111,10 @@ def build_run(root: Path, run_dir: Path) -> dict | None:
     eval_id = None
 
     # Try eval_metadata.json
-    for candidate in [run_dir / "eval_metadata.json", run_dir.parent / "eval_metadata.json"]:
+    for candidate in [
+        run_dir / "eval_metadata.json",
+        run_dir.parent / "eval_metadata.json",
+    ]:
         if candidate.exists():
             try:
                 metadata = json.loads(candidate.read_text(encoding="utf-8"))
@@ -101,7 +127,10 @@ def build_run(root: Path, run_dir: Path) -> dict | None:
 
     # Fall back to transcript.md
     if not prompt:
-        for candidate in [run_dir / "transcript.md", run_dir / "outputs" / "transcript.md"]:
+        for candidate in [
+            run_dir / "transcript.md",
+            run_dir / "outputs" / "transcript.md",
+        ]:
             if candidate.exists():
                 try:
                     text = candidate.read_text(encoding="utf-8")
@@ -166,7 +195,11 @@ def embed_file(path: Path) -> dict:
             raw = path.read_bytes()
             b64 = base64.b64encode(raw).decode("ascii")
         except OSError:
-            return {"name": path.name, "type": "error", "content": "(Error reading file)"}
+            return {
+                "name": path.name,
+                "type": "error",
+                "content": "(Error reading file)",
+            }
         return {
             "name": path.name,
             "type": "image",
@@ -178,7 +211,11 @@ def embed_file(path: Path) -> dict:
             raw = path.read_bytes()
             b64 = base64.b64encode(raw).decode("ascii")
         except OSError:
-            return {"name": path.name, "type": "error", "content": "(Error reading file)"}
+            return {
+                "name": path.name,
+                "type": "error",
+                "content": "(Error reading file)",
+            }
         return {
             "name": path.name,
             "type": "pdf",
@@ -189,7 +226,11 @@ def embed_file(path: Path) -> dict:
             raw = path.read_bytes()
             b64 = base64.b64encode(raw).decode("ascii")
         except OSError:
-            return {"name": path.name, "type": "error", "content": "(Error reading file)"}
+            return {
+                "name": path.name,
+                "type": "error",
+                "content": "(Error reading file)",
+            }
         return {
             "name": path.name,
             "type": "xlsx",
@@ -201,7 +242,11 @@ def embed_file(path: Path) -> dict:
             raw = path.read_bytes()
             b64 = base64.b64encode(raw).decode("ascii")
         except OSError:
-            return {"name": path.name, "type": "error", "content": "(Error reading file)"}
+            return {
+                "name": path.name,
+                "type": "error",
+                "content": "(Error reading file)",
+            }
         return {
             "name": path.name,
             "type": "binary",
@@ -278,19 +323,24 @@ def generate_html(
 
     data_json = json.dumps(embedded)
 
-    return template.replace("/*__EMBEDDED_DATA__*/", f"const EMBEDDED_DATA = {data_json};")
+    return template.replace(
+        "/*__EMBEDDED_DATA__*/", f"const EMBEDDED_DATA = {data_json};"
+    )
 
 
 # ---------------------------------------------------------------------------
 # HTTP server (stdlib only, zero dependencies)
 # ---------------------------------------------------------------------------
 
+
 def _kill_port(port: int) -> None:
     """Kill any process listening on the given port."""
     try:
         result = subprocess.run(
             ["lsof", "-ti", f":{port}"],
-            capture_output=True, text=True, timeout=5,
+            capture_output=True,
+            text=True,
+            timeout=5,
         )
         for pid_str in result.stdout.strip().split("\n"):
             if pid_str.strip():
@@ -305,6 +355,7 @@ def _kill_port(port: int) -> None:
     except FileNotFoundError:
         print("Note: lsof not found, cannot check if port is in use", file=sys.stderr)
 
+
 class ReviewHandler(BaseHTTPRequestHandler):
     """Serves the review HTML and handles feedback saves.
 
@@ -336,7 +387,9 @@ class ReviewHandler(BaseHTTPRequestHandler):
             benchmark = None
             if self.benchmark_path and self.benchmark_path.exists():
                 try:
-                    benchmark = json.loads(self.benchmark_path.read_text(encoding="utf-8"))
+                    benchmark = json.loads(
+                        self.benchmark_path.read_text(encoding="utf-8")
+                    )
                 except (json.JSONDecodeError, OSError):
                     pass
             html = generate_html(runs, self.skill_name, self.previous, benchmark)
@@ -366,7 +419,9 @@ class ReviewHandler(BaseHTTPRequestHandler):
                 data = json.loads(body)
                 if not isinstance(data, dict) or "reviews" not in data:
                     raise ValueError("Expected JSON object with 'reviews' key")
-                self.feedback_path.write_text(json.dumps(data, indent=2, encoding="utf-8") + "\n")
+                self.feedback_path.write_text(
+                    json.dumps(data, indent=2) + "\n", encoding="utf-8"
+                )
                 resp = b'{"ok":true}'
                 self.send_response(200)
             except (json.JSONDecodeError, OSError, ValueError) as e:
@@ -387,18 +442,29 @@ class ReviewHandler(BaseHTTPRequestHandler):
 def main() -> None:
     parser = argparse.ArgumentParser(description="Generate and serve eval review")
     parser.add_argument("workspace", type=Path, help="Path to workspace directory")
-    parser.add_argument("--port", "-p", type=int, default=3117, help="Server port (default: 3117)")
-    parser.add_argument("--skill-name", "-n", type=str, default=None, help="Skill name for header")
     parser.add_argument(
-        "--previous-workspace", type=Path, default=None,
+        "--port", "-p", type=int, default=3117, help="Server port (default: 3117)"
+    )
+    parser.add_argument(
+        "--skill-name", "-n", type=str, default=None, help="Skill name for header"
+    )
+    parser.add_argument(
+        "--previous-workspace",
+        type=Path,
+        default=None,
         help="Path to previous iteration's workspace (shows old outputs and feedback as context)",
     )
     parser.add_argument(
-        "--benchmark", type=Path, default=None,
+        "--benchmark",
+        type=Path,
+        default=None,
         help="Path to benchmark.json to show in the Benchmark tab",
     )
     parser.add_argument(
-        "--static", "-s", type=Path, default=None,
+        "--static",
+        "-s",
+        type=Path,
+        default=None,
         help="Write standalone HTML to this path instead of starting a server",
     )
     args = parser.parse_args()
@@ -438,7 +504,9 @@ def main() -> None:
     # Kill any existing process on the target port
     port = args.port
     _kill_port(port)
-    handler = partial(ReviewHandler, workspace, skill_name, feedback_path, previous, benchmark_path)
+    handler = partial(
+        ReviewHandler, workspace, skill_name, feedback_path, previous, benchmark_path
+    )
     try:
         server = HTTPServer(("127.0.0.1", port), handler)
     except OSError:

{docagent_cli-0.0.41 → docagent_cli-0.0.42}/docagent_cli/built_in_skills/skill-creator/scripts/improve_description.py

@@ -60,18 +60,20 @@ def improve_description(
 ) -> str:
     """Call Claude to improve the description based on eval results."""
     failed_triggers = [
-        r for r in eval_results["results"]
-        if r["should_trigger"] and not r["pass"]
+        r for r in eval_results["results"] if r["should_trigger"] and not r["pass"]
     ]
     false_triggers = [
-        r for r in eval_results["results"]
-        if not r["should_trigger"] and not r["pass"]
+        r for r in eval_results["results"] if not r["should_trigger"] and not r["pass"]
     ]
 
     # Build scores summary
-    train_score = f"{eval_results['summary']['passed']}/{eval_results['summary']['total']}"
+    train_score = (
+        f"{eval_results['summary']['passed']}/{eval_results['summary']['total']}"
+    )
     if test_results:
-        test_score = f"{test_results['summary']['passed']}/{test_results['summary']['total']}"
+        test_score = (
+            f"{test_results['summary']['passed']}/{test_results['summary']['total']}"
+        )
         scores_summary = f"Train: {train_score}, Test: {test_score}"
     else:
         scores_summary = f"Train: {train_score}"
@@ -91,22 +93,30 @@ Current scores ({scores_summary}):
     if failed_triggers:
         prompt += "FAILED TO TRIGGER (should have triggered but didn't):\n"
         for r in failed_triggers:
-            prompt += f'  - "{r["query"]}" (triggered {r["triggers"]}/{r["runs"]} times)\n'
+            prompt += (
+                f'  - "{r["query"]}" (triggered {r["triggers"]}/{r["runs"]} times)\n'
+            )
         prompt += "\n"
 
     if false_triggers:
         prompt += "FALSE TRIGGERS (triggered but shouldn't have):\n"
         for r in false_triggers:
-            prompt += f'  - "{r["query"]}" (triggered {r["triggers"]}/{r["runs"]} times)\n'
+            prompt += (
+                f'  - "{r["query"]}" (triggered {r["triggers"]}/{r["runs"]} times)\n'
+            )
         prompt += "\n"
 
     if history:
         prompt += "PREVIOUS ATTEMPTS (do NOT repeat these — try something structurally different):\n\n"
         for h in history:
             train_s = f"{h.get('train_passed', h.get('passed', 0))}/{h.get('train_total', h.get('total', 0))}"
-            test_s = f"{h.get('test_passed', '?')}/{h.get('test_total', '?')}" if h.get('test_passed') is not None else None
+            test_s = (
+                f"{h.get('test_passed', '?')}/{h.get('test_total', '?')}"
+                if h.get("test_passed") is not None
+                else None
+            )
             score_str = f"train={train_s}" + (f", test={test_s}" if test_s else "")
-            prompt += f'<attempt {score_str}>\n'
+            prompt += f"<attempt {score_str}>\n"
             prompt += f'Description: "{h["description"]}"\n'
             if "results" in h:
                 prompt += "Train results:\n"
@@ -114,7 +124,7 @@ Current scores ({scores_summary}):
                     status = "PASS" if r["pass"] else "FAIL"
                     prompt += f'  [{status}] "{r["query"][:80]}" (triggered {r["triggers"]}/{r["runs"]})\n'
             if h.get("note"):
-                prompt += f'Note: {h["note"]}\n'
+                prompt += f"Note: {h['note']}\n"
             prompt += "</attempt>\n\n"
 
     prompt += f"""</scores_summary>
@@ -137,14 +147,16 @@ Here are some tips that we've found to work well in writing these descriptions:
 - The description competes with other skills for Claude's attention — make it distinctive and immediately recognizable.
 - If you're getting lots of failures after repeated attempts, change things up. Try different sentence structures or wordings.
 
-I'd encourage you to be creative and mix up the style in different iterations since you'll have multiple opportunities to try different approaches and we'll just grab the highest-scoring one at the end. 
+I'd encourage you to be creative and mix up the style in different iterations since you'll have multiple opportunities to try different approaches and we'll just grab the highest-scoring one at the end.
 
 Please respond with only the new description text in <new_description> tags, nothing else."""
 
     text = _call_claude(prompt, model)
 
     match = re.search(r"<new_description>(.*?)</new_description>", text, re.DOTALL)
-    description = match.group(1).strip().strip('"') if match else text.strip().strip('"')
+    description = (
+        match.group(1).strip().strip('"') if match else text.strip().strip('"')
+    )
 
     transcript: dict = {
         "iteration": iteration,
@@ -172,8 +184,14 @@ Please respond with only the new description text in <new_description> tags, not
             f"the new description in <new_description> tags."
         )
         shorten_text = _call_claude(shorten_prompt, model)
-        match = re.search(r"<new_description>(.*?)</new_description>", shorten_text, re.DOTALL)
-        shortened = match.group(1).strip().strip('"') if match else shorten_text.strip().strip('"')
+        match = re.search(
+            r"<new_description>(.*?)</new_description>", shorten_text, re.DOTALL
+        )
+        shortened = (
+            match.group(1).strip().strip('"')
+            if match
+            else shorten_text.strip().strip('"')
+        )
 
         transcript["rewrite_prompt"] = shorten_prompt
         transcript["rewrite_response"] = shorten_text
@@ -186,18 +204,28 @@ Please respond with only the new description text in <new_description> tags, not
     if log_dir:
         log_dir.mkdir(parents=True, exist_ok=True)
         log_file = log_dir / f"improve_iter_{iteration or 'unknown'}.json"
-        log_file.write_text(json.dumps(transcript, indent=2, encoding="utf-8"))
+        log_file.write_text(json.dumps(transcript, indent=2), encoding="utf-8")
 
     return description
 
 
 def main():
-    parser = argparse.ArgumentParser(description="Improve a skill description based on eval results")
-    parser.add_argument("--eval-results", required=True, help="Path to eval results JSON (from run_eval.py)")
+    parser = argparse.ArgumentParser(
+        description="Improve a skill description based on eval results"
+    )
+    parser.add_argument(
+        "--eval-results",
+        required=True,
+        help="Path to eval results JSON (from run_eval.py)",
+    )
     parser.add_argument("--skill-path", required=True, help="Path to skill directory")
-    parser.add_argument("--history", default=None, help="Path to history JSON (previous attempts)")
+    parser.add_argument(
+        "--history", default=None, help="Path to history JSON (previous attempts)"
+    )
     parser.add_argument("--model", required=True, help="Model for improvement")
-    parser.add_argument("--verbose", action="store_true", help="Print thinking to stderr")
+    parser.add_argument(
+        "--verbose", action="store_true", help="Print thinking to stderr"
+    )
     args = parser.parse_args()
 
     skill_path = Path(args.skill_path)
@@ -215,7 +243,10 @@ def main():
 
     if args.verbose:
         print(f"Current: {current_description}", file=sys.stderr)
-        print(f"Score: {eval_results['summary']['passed']}/{eval_results['summary']['total']}", file=sys.stderr)
+        print(
+            f"Score: {eval_results['summary']['passed']}/{eval_results['summary']['total']}",
+            file=sys.stderr,
+        )
 
     new_description = improve_description(
         skill_name=name,
@@ -232,13 +263,16 @@ def main():
     # Output as JSON with both the new description and updated history
     output = {
         "description": new_description,
-        "history": history + [{
-            "description": current_description,
-            "passed": eval_results["summary"]["passed"],
-            "failed": eval_results["summary"]["failed"],
-            "total": eval_results["summary"]["total"],
-            "results": eval_results["results"],
-        }],
+        "history": history
+        + [
+            {
+                "description": current_description,
+                "passed": eval_results["summary"]["passed"],
+                "failed": eval_results["summary"]["failed"],
+                "total": eval_results["summary"]["total"],
+                "results": eval_results["results"],
+            }
+        ],
     }
     print(json.dumps(output, indent=2))
 

{docagent_cli-0.0.41 → docagent_cli-0.0.42}/docagent_cli/server.py

@@ -114,7 +114,7 @@ def generate_langgraph_json(
         config["checkpointer"] = {"path": checkpointer_path}
 
     output_path = Path(output_dir) / "langgraph.json"
-    output_path.write_text(json.dumps(config, indent=2, encoding="utf-8"))
+    output_path.write_text(json.dumps(config, indent=2), encoding="utf-8")
     return output_path
 
 
@@ -206,7 +206,7 @@ async def wait_for_server_healthy(
                     _marker = "Failed to initialize server graph:"
                     _idx = output.find(_marker)
                     if _idx != -1:
-                        msg += f"\n{output[_idx:_idx + 2000]}"
+                        msg += f"\n{output[_idx : _idx + 2000]}"
                     else:
                         msg += f"\n{output[-3000:]}"
                 raise RuntimeError(msg)

{docagent_cli-0.0.41 → docagent_cli-0.0.42}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "docagent-cli"
-version = "0.0.41"
+version = "0.0.42"
 description = "Terminal interface for Deep Agents - interactive AI agent with file operations, shell access, and sub-agent capabilities."
 readme = "README.md"
 license = { text = "MIT" }

{docagent_cli-0.0.41 → docagent_cli-0.0.42}/uv.lock

@@ -1151,7 +1151,7 @@ test = [
 
 [[package]]
 name = "docagent-cli"
-version = "0.0.40"
+version = "0.0.41"
 source = { editable = "." }
 dependencies = [
     { name = "aiosqlite" },