docs(conversation): align runtime model env vars & update component examples

- Add and document runtime env vars: OPENAI_MODEL, AZURE_OPENAI_MODEL, ANTHROPIC_MODEL, GOOGLEAI_MODEL, MISTRAL_MODEL, HUGGINGFACE_MODEL, OLLAMA_MODEL (with defaults)
- Update environment reference page with the new env var names and defaults
- Replace env-var placeholders in component YAML examples with literal default model names for OpenAI, GoogleAI, Anthropic, Mistral, Hugging Face and Ollama
- Add "(configurable via '<ENV>' environment variable)" to each provider's Spec metadata table to show override option
- Add Azure OpenAI usage section to `conversation.openai` doc (how to use `apiType: azure` and `AZURE_OPENAI_MODEL`)
- Clarify AWS Bedrock uses standard AWS auth (no Bedrock-specific env var added)
- Fix small markdown lint issues (trailing newlines/whitespace)

Signed-off-by: Erin La <107987318+giterinhub@users.noreply.github.com>

Author: giterinhub

daprdocs/content/en/reference/components-reference/supported-conversation/anthropic.md

@@ -20,7 +20,7 @@ spec:
   - name: key
     value: "mykey"
   - name: model
-  value: '${{DAPR_CONVERSATION_ANTHROPIC_MODEL}}'
+  value: 'claude-sonnet-4-20250514'
   - name: cacheTTL
     value: 10m
 ```
@@ -34,9 +34,9 @@ The above example uses secrets as plain strings. It is recommended to use a secr
 | Field              | Required | Details | Example |
 |--------------------|:--------:|---------|---------|
 | `key`   | Y | API key for Anthropic. | `"mykey"` |
-| `model` | N | The Anthropic LLM to use. Defaults to `claude-3-5-sonnet-20240620` (configurable via `DAPR_CONVERSATION_ANTHROPIC_MODEL` environment variable).  | `${{DAPR_CONVERSATION_ANTHROPIC_MODEL}}` |
+| `model` | N | The Anthropic LLM to use. Defaults to `claude-sonnet-4-20250514` (configurable via the `ANTHROPIC_MODEL` environment variable).  | `claude-sonnet-4-20250514` |
 | `cacheTTL` | N | A time-to-live value for a prompt cache to expire. Uses Golang duration format.  | `10m` |
 
 ## Related links
 
-- [Conversation API overview]({{< ref conversation-overview.md >}})
+- [Conversation API overview]({{< ref conversation-overview.md >}})

daprdocs/content/en/reference/components-reference/supported-conversation/googleai.md

@@ -20,7 +20,7 @@ spec:
   - name: key
     value: "mykey"
   - name: model
-    value: '${{DAPR_CONVERSATION_GOOGLEAI_MODEL}}'
+    value: 'gemini-2.5-flash-lite'
   - name: cacheTTL
     value: 10m
 ```
@@ -34,7 +34,7 @@ The above example uses secrets as plain strings. It is recommended to use a secr
 | Field              | Required | Details | Example |
 |--------------------|:--------:|---------|---------|
 | `key`   | Y | API key for GoogleAI. | `"mykey"` |
-| `model` | N | The GoogleAI LLM to use. Defaults to `gemini-1.5-flash` (configurable via `DAPR_CONVERSATION_GOOGLEAI_MODEL` environment variable).  | `${{DAPR_CONVERSATION_GOOGLEAI_MODEL}}` |
+| `model` | N | The GoogleAI LLM to use. Defaults to `gemini-2.5-flash-lite` (configurable via the `GOOGLEAI_MODEL` environment variable).  | `gemini-2.5-flash-lite` |
 | `cacheTTL` | N | A time-to-live value for a prompt cache to expire. Uses Golang duration format.  | `10m` |
 
 ## Related links

daprdocs/content/en/reference/components-reference/supported-conversation/hugging-face.md

@@ -20,7 +20,7 @@ spec:
   - name: key
     value: mykey
   - name: model
-  value: '${{DAPR_CONVERSATION_HUGGINGFACE_MODEL}}'
+  value: 'deepseek-ai/DeepSeek-R1-Distill-Qwen-32B'
   - name: cacheTTL
     value: 10m
 ```
@@ -34,9 +34,9 @@ The above example uses secrets as plain strings. It is recommended to use a secr
 | Field              | Required | Details | Example |
 |--------------------|:--------:|---------|---------|
 | `key`   | Y | API key for Huggingface. | `mykey` |
-| `model` | N | The Huggingface LLM to use. Defaults to `deepseek-ai/DeepSeek-R1-Distill-Qwen-32B` (configurable via `DAPR_CONVERSATION_HUGGINGFACE_MODEL` environment variable).  | `${{DAPR_CONVERSATION_HUGGINGFACE_MODEL}}` |
+| `model` | N | The Huggingface LLM to use. Defaults to `deepseek-ai/DeepSeek-R1-Distill-Qwen-32B` (configurable via the `HUGGINGFACE_MODEL` environment variable).  | `deepseek-ai/DeepSeek-R1-Distill-Qwen-32B` |
 | `cacheTTL` | N | A time-to-live value for a prompt cache to expire. Uses Golang duration format.  | `10m` |
 
 ## Related links
 
-- [Conversation API overview]({{< ref conversation-overview.md >}})
+- [Conversation API overview]({{< ref conversation-overview.md >}})

daprdocs/content/en/reference/components-reference/supported-conversation/mistral.md

@@ -20,7 +20,7 @@ spec:
   - name: key
     value: mykey
   - name: model
-  value: '${{DAPR_CONVERSATION_MISTRAL_MODEL}}'
+  value: 'open-mistral-7b'
   - name: cacheTTL
     value: 10m
 ```
@@ -34,9 +34,9 @@ The above example uses secrets as plain strings. It is recommended to use a secr
 | Field              | Required | Details | Example |
 |--------------------|:--------:|---------|---------|
 | `key`   | Y | API key for Mistral. | `mykey` |
-| `model` | N | The Mistral LLM to use. Defaults to `open-mistral-7b` (configurable via `DAPR_CONVERSATION_MISTRAL_MODEL` environment variable).  | `${{DAPR_CONVERSATION_MISTRAL_MODEL}}` |
+| `model` | N | The Mistral LLM to use. Defaults to `open-mistral-7b` (configurable via the `MISTRAL_MODEL` environment variable).  | `open-mistral-7b` |
 | `cacheTTL` | N | A time-to-live value for a prompt cache to expire. Uses Golang duration format.  | `10m` |
 
 ## Related links
 
-- [Conversation API overview]({{< ref conversation-overview.md >}})
+- [Conversation API overview]({{< ref conversation-overview.md >}})

daprdocs/content/en/reference/components-reference/supported-conversation/ollama.md

@@ -18,7 +18,7 @@ spec:
   type: conversation.ollama
   metadata:
   - name: model
-    value: '${{DAPR_CONVERSATION_OLLAMA_MODEL}}'
+    value: 'llama3.2:latest'
   - name: cacheTTL
     value: 10m
 ```
@@ -31,7 +31,7 @@ The above example uses secrets as plain strings. It is recommended to use a secr
 
 | Field              | Required | Details | Example |
 |--------------------|:--------:|---------|---------|
-| `model` | N | The Ollama LLM to use. Defaults to `llama3.2:latest` (configurable via `DAPR_CONVERSATION_OLLAMA_MODEL` environment variable).  | `${{DAPR_CONVERSATION_OLLAMA_MODEL}}` |
+| `model` | N | The Ollama LLM to use. Defaults to `llama3.2:latest` (configurable via the `OLLAMA_MODEL` environment variable).  | `llama3.2:latest` |
 | `cacheTTL` | N | A time-to-live value for a prompt cache to expire. Uses Golang duration format.  | `10m` |
 
 ## Related links

daprdocs/content/en/reference/components-reference/supported-conversation/openai.md

@@ -20,7 +20,7 @@ spec:
   - name: key
     value: mykey
   - name: model
-  value: '${{DAPR_CONVERSATION_OPENAI_MODEL}}'
+    value: 'gpt-5-nano'
   - name: cacheTTL
     value: 10m
 ```
@@ -34,9 +34,33 @@ The above example uses secrets as plain strings. It is recommended to use a secr
 | Field              | Required | Details | Example |
 |--------------------|:--------:|---------|---------|
 | `key`   | Y | API key for OpenAI. | `mykey` |
-| `model` | N | The OpenAI LLM to use. Defaults to `gpt-5-nano` (configurable via `DAPR_CONVERSATION_OPENAI_MODEL` environment variable).  | `${{DAPR_CONVERSATION_OPENAI_MODEL}}` |
+| `model` | N | The OpenAI LLM to use. Defaults to `gpt-5-nano` (configurable via the `OPENAI_MODEL` environment variable).  | `gpt-5-nano` |
 | `cacheTTL` | N | A time-to-live value for a prompt cache to expire. Uses Golang duration format.  | `10m` |
 
+## Azure OpenAI usage
+
+The `conversation.openai` component can target either OpenAI's hosted API or Azure OpenAI. To select Azure OpenAI, set the component's `apiType` metadata to `azure` and provide the usual Azure-specific connection settings (for example, endpoint/region and API key) in the component configuration.
+
+When `apiType: azure` is used, the environment variable `AZURE_OPENAI_MODEL` may be set to provide a default Azure model identifier to use when the component's `model` metadata is not provided. This environment variable only affects the component when `apiType` is set to `azure` — the regular `DAPR_CONVERSATION_OPENAI_MODEL` remains the default for non-Azure OpenAI usage.
+
+Example (Azure OpenAI configuration):
+
+```yaml
+spec:
+  type: conversation.openai
+  metadata:
+  - name: apiType
+    value: azure
+  - name: key
+    value: "<your-azure-openai-key>"
+  - name: endpoint
+    value: "https://<your-resource-name>.openai.azure.com/"
+  - name: model
+    value: '${{AZURE_OPENAI_MODEL}}'
+```
+
+If `model` is omitted from the component metadata and neither `AZURE_OPENAI_MODEL` nor `DAPR_CONVERSATION_OPENAI_MODEL` are set, the component falls back to its built-in default model.
+
 ## Related links
 
-- [Conversation API overview]({{< ref conversation-overview.md >}})
+- [Conversation API overview]({{< ref conversation-overview.md >}})

daprdocs/content/en/reference/environment/_index.md

@@ -21,12 +21,20 @@ The following table lists the environment variables used by the Dapr runtime, CL
 | SSL_CERT_DIR | Dapr sidecar | Specifies the location where the public certificates for all the trusted certificate authorities (CA) are located. Not applicable when the sidecar is running as a process in self-hosted mode.|
 | DAPR_HELM_REPO_URL | Your private Dapr Helm chart url  | Specifies a private Dapr Helm chart url, which defaults to the official Helm chart URL: `https://dapr.github.io/helm-charts`|
 | DAPR_HELM_REPO_USERNAME | A username for a private Helm chart | The username required to access the private Dapr Helm chart. If it can be accessed publicly, this env variable does not need to be set|
-| DAPR_HELM_REPO_PASSWORD | A password for a private Helm chart  |The password required to access the private Dapr helm chart. If it can be accessed publicly, this env variable does not need to be set| 
+| DAPR_HELM_REPO_PASSWORD | A password for a private Helm chart  |The password required to access the private Dapr helm chart. If it can be accessed publicly, this env variable does not need to be set|
 | OTEL_EXPORTER_OTLP_ENDPOINT | OpenTelemetry Tracing | Sets the Open Telemetry (OTEL) server address, turns on tracing. (Example: `http://localhost:4318`) |
 | OTEL_EXPORTER_OTLP_INSECURE | OpenTelemetry Tracing | Sets the connection to the endpoint as unencrypted. (`true`, `false`) |
 | OTEL_EXPORTER_OTLP_PROTOCOL | OpenTelemetry Tracing | The OTLP protocol to use Transport protocol. (`grpc`, `http/protobuf`, `http/json`) |
 | DAPR_COMPONENTS_SOCKETS_FOLDER | Dapr runtime and the .NET, Go, and Java pluggable component SDKs | The location or path where Dapr looks for Pluggable Components Unix Domain Socket files. If unset this location defaults to `/tmp/dapr-components-sockets` |
 | DAPR_COMPONENTS_SOCKETS_EXTENSION | .NET and Java pluggable component SDKs | A per-SDK configuration that indicates the default file extension applied to socket files created by the SDKs. Not a Dapr-enforced behavior. |
 | DAPR_PLACEMENT_METADATA_ENABLED | Dapr placement | Enable an endpoint for the Placement service that exposes placement table information on actor usage. Set to `true` to enable in self-hosted mode. [Learn more about the Placement API]({{< ref placement_api.md >}}) |
 | DAPR_HOST_IP | Dapr sidecar | The host's chosen IP address. If not specified, will loop over the network interfaces and select the first non-loopback address it finds.|
-| DAPR_HEALTH_TIMEOUT | SDKs | Sets the time on the "wait for sidecar" availability. Overrides the default timeout setting of 60 seconds. |
+| DAPR_HEALTH_TIMEOUT | SDKs | Sets the time on the "wait for sidecar" availability. Overrides the default timeout setting of 60 seconds. |
+| OPENAI_MODEL | Conversation components | Default model name used by the `conversation.openai` component at runtime when no `model` metadata is set in the component file. Default: `gpt-5-nano`. |
+| AZURE_OPENAI_MODEL | Conversation components / Azure config | Default Azure model name used by the `conversation.openai` component when `apiType: azure` is configured and no `model` metadata is provided. Default: `gpt-4.1-mini`. |
+| ANTHROPIC_MODEL | Conversation components | Default model name used by the `conversation.anthropic` component when no `model` metadata is set in the component file. Default: `claude-sonnet-4-20250514`. |
+| GOOGLEAI_MODEL | Conversation components | Default model name used by the `conversation.googleai` component when no `model` metadata is set in the component file. Default: `gemini-2.5-flash-lite`. |
+| MISTRAL_MODEL | Conversation components | Default model name used by the `conversation.mistral` component when no `model` metadata is set in the component file. Default: `open-mistral-7b`. |
+| HUGGINGFACE_MODEL | Conversation components | Default model name used by the `conversation.huggingface` component when no `model` metadata is set in the component file. Default: `deepseek-ai/DeepSeek-R1-Distill-Qwen-32B`. |
+| OLLAMA_MODEL | Conversation components | Default model name used by the `conversation.ollama` component when no `model` metadata is set in the component file. Default: `llama3.2:latest`. |
+