Fix output truncation bug, add language support for agent responses

Bug 1 — Output truncation:
  _run_claude() was replacing raw stdout with parsed sub-field which
  could be a dict (not string). run_agent() then saved dict.__repr__
  to DB instead of full JSON. Fixed: _run_claude() always returns
  string output; run_agent() ensures string before DB write.
  Added tests: full_output_saved_to_db, dict_output_saved_as_json_string.

Bug 2 — Language support:
  Added projects.language column (TEXT DEFAULT 'ru').
  Auto-migration for existing DBs (ALTER TABLE ADD COLUMN).
  context_builder passes language in project context.
  format_prompt() appends "## Language\nALWAYS respond in {language}"
  at the end of every prompt.
  CLI: kin project add --language ru (default: ru).
  Tests: language in prompt for ru/en, project creation, context.

112 tests, all passing. ~/.kin/kin.db migrated (vdol: language=ru).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

agents/runner.py

@@ -65,12 +65,15 @@ def run_agent(
     result = _run_claude(prompt, model=model, working_dir=working_dir)
     duration = int(time.monotonic() - start)
 
-    # Parse output
-    output_text = result.get("output", "")
+    # Parse output — ensure output_text is always a string for DB storage
+    raw_output = result.get("output", "")
+    if not isinstance(raw_output, str):
+        raw_output = json.dumps(raw_output, ensure_ascii=False)
+    output_text = raw_output
     success = result["returncode"] == 0
     parsed_output = _try_parse_json(output_text)
 
-    # Log to DB
+    # Log FULL output to DB (no truncation)
     models.log_agent_run(
         conn,
         project_id=project_id,
@@ -133,24 +136,24 @@ def _run_claude(
             "returncode": 124,
         }
 
-    # Try to extract structured data from JSON output
-    output = proc.stdout or ""
+    # Always preserve the full raw stdout
+    raw_stdout = proc.stdout or ""
     result: dict[str, Any] = {
-        "output": output,
+        "output": raw_stdout,
         "error": proc.stderr if proc.returncode != 0 else None,
         "returncode": proc.returncode,
     }
 
-    # Parse JSON output from claude --output-format json
-    parsed = _try_parse_json(output)
+    # Parse JSON wrapper from claude --output-format json
+    # Extract metadata (tokens, cost) but keep output as the full content string
+    parsed = _try_parse_json(raw_stdout)
     if isinstance(parsed, dict):
         result["tokens_used"] = parsed.get("usage", {}).get("total_tokens")
         result["cost_usd"] = parsed.get("cost_usd")
-        # The actual content is usually in result or content
-        if "result" in parsed:
-            result["output"] = parsed["result"]
-        elif "content" in parsed:
-            result["output"] = parsed["content"]
+        # Extract the agent's actual response, converting to string if needed
+        content = parsed.get("result") or parsed.get("content")
+        if content is not None:
+            result["output"] = content if isinstance(content, str) else json.dumps(content, ensure_ascii=False)
 
     return result