docs: fixing typo in multiple files

Merge https://github.com/google/adk-python/pull/3944

### Link to Issue or Description of Change

**1. Link to an existing issue (if applicable):** N/A

**2. Or, if no issue exists, describe the change:** fixing various typos in multiple files: see commit diffs for details

**Problem:**

Discovered typos while reading ADK repo

**Solution:**

Submitted this PR to fix them

### Testing Plan

N/A: changes only in comments, .md and docstrings.

**Unit Tests:**

- [N/A ] I have added or updated unit tests for my change.
- [X] All unit tests pass locally.

_Please include a summary of passed `pytest` results._

**Manual End-to-End (E2E) Tests:**

N/A

### Checklist

- [X] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [X] I have performed a self-review of my own code.
- [N/A] I have commented my code, particularly in hard-to-understand areas.
- [N/A] I have added tests that prove my fix is effective or that my feature works.
- [X] New and existing unit tests pass locally with my changes.
- [N/A] I have manually tested my changes end-to-end.
- [N/A] Any dependent changes have been merged and published in downstream modules.

### Additional context

N/A

COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3944 from didier-durand:fix-typos-a 02378a488d9a87ac9b6b7397fe9ad7c393faf16a
PiperOrigin-RevId: 868245940

contributing/samples/gepa/adk_agent.py

@@ -159,7 +159,7 @@ def _adk_agent(
 
 
 class _UserAgent(base_agent.BaseAgent):
-  """An agent that wraps the provided environment and simulates an user."""
+  """An agent that wraps the provided environment and simulates a user."""
 
   env: Env
 

contributing/samples/gepa/tau_bench_agent.py

@@ -103,7 +103,7 @@ class _ADKAgent(tool_calling_agent.ToolCallingAgent):
       max_num_steps: The maximum number of steps to run the agent.
 
     Returns:
-      The result of the solve.
+      The result of the solve function.
 
     Raises:
       - ValueError: If the LLM inference failed.

src/google/adk/agents/llm_agent.py

@@ -469,7 +469,7 @@ class LlmAgent(BaseAgent):
         self.__maybe_save_output_to_state(event)
         yield event
         if ctx.should_pause_invocation(event):
-          # Do not pause immediately, wait until the long running tool call is
+          # Do not pause immediately, wait until the long-running tool call is
           # executed.
           should_pause = True
     if should_pause:
@@ -479,7 +479,7 @@ class LlmAgent(BaseAgent):
       events = ctx._get_events(current_invocation=True, current_branch=True)
       if events and any(ctx.should_pause_invocation(e) for e in events[-2:]):
         return
-      # Only yield an end state if the last event is no longer a long running
+      # Only yield an end state if the last event is no longer a long-running
       # tool call.
       ctx.set_agent_state(self.name, end_of_agent=True)
       yield self._create_agent_state_event(ctx)

src/google/adk/models/gemini_llm_connection.py

@@ -142,7 +142,7 @@ class GeminiLlmConnection(BaseLlmConnection):
   def __build_full_text_response(self, text: str):
     """Builds a full text response.
 
-    The text should not partial and the returned LlmResponse is not be
+    The text should not be partial and the returned LlmResponse is not
     partial.
 
     Args:

src/google/adk/models/gemma_llm.py

@@ -323,7 +323,7 @@ def _get_last_valid_json_substring(text: str) -> tuple[bool, str | None]:
   """Attempts to find and return the last valid JSON object in a string.
 
   This function is designed to extract JSON that might be embedded in a larger
-  text, potentially with introductory or concluding remarks. It will always chose
+  text, potentially with introductory or concluding remarks. It will always choose
   the last block of valid json found within the supplied text (if it exists).
 
   Args:

src/google/adk/tools/openapi_tool/openapi_spec_parser/tool_auth_handler.py

@@ -321,7 +321,7 @@ class ToolAuthHandler:
     credential = existing_credential or self.auth_credential
     # fetch credential from adk framework
     # Some auth scheme like OAuth2 AuthCode & OpenIDConnect may require
-    # multi-step exchange:
+    # multistep exchange:
     # client_id , client_secret -> auth_uri -> auth_code -> access_token
     # adk framework supports exchange access_token already
     # for other credential, adk can also get back the credential directly

tests/integration/fixture/home_automation_agent/agent.py

@@ -138,29 +138,29 @@ def set_device_info(
 
 
 def get_temperature(location: str) -> int:
-  """Get the current temperature in celsius of a location (e.g., 'Living Room', 'Bedroom', 'Kitchen').
+  """Get the current temperature in Celsius of a location (e.g., 'Living Room', 'Bedroom', 'Kitchen').
 
   Args:
       location (str): The location for which to retrieve the temperature (e.g.,
         'Living Room', 'Bedroom', 'Kitchen').
 
   Returns:
-      int: The current temperature in celsius in the specified location, or
+      int: The current temperature in Celsius in the specified location, or
       'Location not found' if the location does not exist.
   """
   return TEMPERATURE_DB.get(location, "Location not found")
 
 
 def set_temperature(location: str, temperature: int) -> str:
-  """Set the desired temperature in celsius for a location.
+  """Set the desired temperature in Celsius for a location.
 
-  Acceptable range of temperature: 18-30 celsius. If it's out of the range, do
+  Acceptable range of temperature: 18-30 Celsius. If it's out of the range, do
   not call this tool.
 
   Args:
       location (str): The location where the temperature should be set.
-      temperature (int): The desired temperature as integer to set in celsius.
-        Acceptable range: 18-30 celsius.
+      temperature (int): The desired temperature as integer to set in Celsius.
+        Acceptable range: 18-30 Celsius.
 
   Returns:
       str: A message indicating whether the temperature was successfully set.