Found docs updates needed from ADK python release v1.32.0 to v1.33.0

Compare URL: https://github.com/google/adk-python/compare/v1.32.0...v1.33.0

### 1. **Support for `max_output_chars` in `EnvironmentToolset`**

**Doc file**: docs/integrations/environment-toolset.md

**Current state**:
> ## Get started
>
> Enable local environment interactions by adding the ***EnvironmentToolset***
> with a ***LocalEnvironment*** instance to your agent's tools.

**Proposed Change**:
> ## Get started
>
> Enable local environment interactions by adding the ***EnvironmentToolset***
> with a ***LocalEnvironment*** instance to your agent's tools.
>
> You can use the optional `max_output_chars` parameter when initializing `EnvironmentToolset` to limit the maximum number of characters returned from file reads or command executions. This helps prevent large file contents or command outputs from exceeding the agent's context window limit.

**Reasoning**:
The `EnvironmentToolset` was updated to accept `max_output_chars` which controls output truncation for `ReadFileTool` and `ExecuteTool`. This helps users prevent their agents' context windows from being overwhelmed by large file/command outputs.

**Reference**: src/google/adk/tools/environment/_environment_toolset.py

---

### 2. **Document `AGENT_RESPONSE` in BigQuery Analytics Event Summary Table**

**Doc file**: docs/integrations/bigquery-agent-analytics.md

**Current state**:
> | `AGENT_STARTING` | Agent execution begins | instruction summary | `v_agent_starting` |
> | `AGENT_COMPLETED` | Agent execution ends | latency | `v_agent_completed` |
> | `LLM_REQUEST` | A model request is sent | model, prompt, config, tools | `v_llm_request` |

**Proposed Change**:
> | `AGENT_STARTING` | Agent execution begins | instruction summary | `v_agent_starting` |
> | `AGENT_COMPLETED` | Agent execution ends | latency | `v_agent_completed` |
> | `AGENT_RESPONSE` | Final response text emitted by the agent | response text, source event ID | `v_agent_response` |
> | `LLM_REQUEST` | A model request is sent | model, prompt, config, tools | `v_llm_request` |

**Reasoning**:
The BigQuery Agent Analytics Plugin now detects and logs final responses emitted by agents as a distinct `AGENT_RESPONSE` event type, which captures the actual visible response text. This needs to be documented in the event summary table.

**Reference**: src/google/adk/plugins/bigquery_agent_analytics_plugin.py

---

### 3. **Document `v_agent_response` View in BigQuery Analytics**

**Doc file**: docs/integrations/bigquery-agent-analytics.md

**Current state**:
> | **`v_agent_starting`** | `agent_instruction` (STRING) |
> | **`v_agent_completed`** | `total_ms` (INT64) |
> | **`v_invocation_starting`** | *(common columns only)* |

**Proposed Change**:
> | **`v_agent_starting`** | `agent_instruction` (STRING) |
> | **`v_agent_completed`** | `total_ms` (INT64) |
> | **`v_agent_response`** | `response_text` (STRING), `source_event_id` (STRING), `source_event_author` (STRING), `source_event_branch` (STRING) |
> | **`v_invocation_starting`** | *(common columns only)* |

**Reasoning**:
The BigQuery Agent Analytics Plugin now automatically creates a `v_agent_response` view for the new `AGENT_RESPONSE` event. This needs to be documented in the auto-created views table.

**Reference**: src/google/adk/plugins/bigquery_agent_analytics_plugin.py

---

### 4. **Document `AGENT_RESPONSE` JSON Payload Structure**

**Doc file**: docs/integrations/bigquery-agent-analytics.md

**Current state**:
> | `AGENT_STARTING` | `"You are a helpful agent..."` |
> | `AGENT_COMPLETED` | `{}` |
> | `USER_MESSAGE_RECEIVED` | `{"text_summary": "Help me book a flight."}` |

**Proposed Change**:
> | `AGENT_STARTING` | `"You are a helpful agent..."` |
> | `AGENT_COMPLETED` | `{}` |
> | `AGENT_RESPONSE` | `{"response": "Final text output from the agent"}` |
> | `USER_MESSAGE_RECEIVED` | `{"text_summary": "Help me book a flight."}` |

**Reasoning**:
The new `AGENT_RESPONSE` event type and its JSON payload structure should be listed under the Agent lifecycle & Generic Events table.

**Reference**: src/google/adk/plugins/bigquery_agent_analytics_plugin.py

---

### 5. **Support for `credentials` parameter in `ApigeeLlm`**

**Doc file**: docs/agents/models/apigee.md

**Current state**:
> === "Python"
>
> ```python
>
> from google.adk.agents import LlmAgent
> from google.adk.models.apigee_llm import ApigeeLlm
>
> # Instantiate the ApigeeLlm wrapper
> model = ApigeeLlm(
> # Specify the Apigee route to your model. For more info, check out the ApigeeLlm documentation (https://github.com/google/adk-python/tree/main/contributing/samples/hello_world_apigeellm).
> model="apigee/gemini-flash-latest",
> # The proxy URL of your deployed Apigee proxy including the base path
> proxy_url=f"https://{APIGEE_PROXY_URL}",
> # Pass necessary authentication/authorization headers (like an API key)
> custom_headers={"foo": "bar"}
> )

**Proposed Change**:
> === "Python"
>
> ```python
>
> from google.adk.agents import LlmAgent
> from google.adk.models.apigee_llm import ApigeeLlm
>
> # Instantiate the ApigeeLlm wrapper
> model = ApigeeLlm(
> # Specify the Apigee route to your model. For more info, check out the ApigeeLlm documentation (https://github.com/google/adk-python/tree/main/contributing/samples/hello_world_apigeellm).
> model="apigee/gemini-flash-latest",
> # The proxy URL of your deployed Apigee proxy including the base path
> proxy_url=f"https://{APIGEE_PROXY_URL}",
> # Pass necessary authentication/authorization headers (like an API key)
> custom_headers={"foo": "bar"},
> # Optional: Pass google-auth credentials if the proxy requires additional OAuth scopes
> # credentials=my_credentials
> )

**Reasoning**:
The ApigeeLlm python wrapper was updated to accept an optional `credentials` parameter to support passing explicit `google-auth` credentials (useful when the Apigee proxy requires additional OAuth scopes like `userinfo.email` for caller identification).

**Reference**: src/google/adk/models/apigee_llm.py