fix(ollama): robustly parse single-quoted JSON in tool calls (#32109)

**Description:**
This PR makes argument parsing for Ollama tool calls more robust. Some
LLMs—including Ollama—may return arguments as Python-style dictionaries
with single quotes (e.g., `{'a': 1}`), which are not valid JSON and
previously caused parsing to fail.
The updated `_parse_json_string` method in
`langchain_ollama.chat_models` now attempts standard JSON parsing and,
if that fails, falls back to `ast.literal_eval` for safe evaluation of
Python-style dictionaries. This improves interoperability with LLMs and
fixes a common usability issue for tool-based agents.

**Issue:**
Closes #30910

**Dependencies:**
None

**Tests:**
- Added new unit tests for double-quoted JSON, single-quoted dicts,
mixed quoting, and malformed/failure cases.
- All tests pass locally, including new coverage for single-quoted
inputs.

**Notes:**
- No breaking changes.
- No new dependencies introduced.
- Code is formatted and linted (`ruff format`, `ruff check`).
- If maintainers have suggestions for further improvements, I’m happy to
revise!

Thank you for maintaining LangChain! Looking forward to your feedback.

libs/langchain/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "pdm.backend"
 [project]
 authors = []
 license = { text = "MIT" }
-requires-python = ">=3.9"
+requires-python = ">=3.9, <4.0"
 dependencies = [
     "langchain-core<1.0.0,>=0.3.66",
     "langchain-text-splitters<1.0.0,>=0.3.8",