fix: use consistent max_tokens defaults across providers

- Fix aliasing issue where resolve_max_tokens() used fallback_default_max_tokens
  (8192) instead of provider-specific defaults
- Update fallback_default_max_tokens from 8192 to 32000
- Set provider-specific max_tokens defaults:
  - Anthropic: 32000
  - OpenAI: 32000 (was 16000)
  - Databricks: 32000 (was 50000, now matches Anthropic as passthru)
  - Embedded: 2048
- Context window lengths unchanged:
  - OpenAI: 400,000
  - Anthropic: 200,000
  - Databricks (Claude): 200,000

This fixes the 'LLM response was cut off due to max_tokens limit' error
in agent mode that occurred because 8192 was being used instead of 32000.

crates/g3-providers/src/databricks.rs

@@ -227,7 +227,7 @@ impl DatabricksProvider {
             host: host.trim_end_matches('/').to_string(),
             auth: DatabricksAuth::token(token),
             model,
-            max_tokens: max_tokens.unwrap_or(50000),
+            max_tokens: max_tokens.unwrap_or(32000),
             temperature: temperature.unwrap_or(0.1),
         })
     }
@@ -254,7 +254,7 @@ impl DatabricksProvider {
             host: host.trim_end_matches('/').to_string(),
             auth: DatabricksAuth::token(token),
             model,
-            max_tokens: max_tokens.unwrap_or(50000),
+            max_tokens: max_tokens.unwrap_or(32000),
             temperature: temperature.unwrap_or(0.1),
         })
     }
@@ -281,7 +281,7 @@ impl DatabricksProvider {
             host: host.trim_end_matches('/').to_string(),
             auth: DatabricksAuth::oauth(host.clone()),
             model,
-            max_tokens: max_tokens.unwrap_or(50000),
+            max_tokens: max_tokens.unwrap_or(32000),
             temperature: temperature.unwrap_or(0.1),
         })
     }
@@ -307,7 +307,7 @@ impl DatabricksProvider {
             host: host.trim_end_matches('/').to_string(),
             auth: DatabricksAuth::oauth(host.clone()),
             model,
-            max_tokens: max_tokens.unwrap_or(50000),
+            max_tokens: max_tokens.unwrap_or(32000),
             temperature: temperature.unwrap_or(0.1),
         })
     }

crates/g3-providers/src/openai.rs

@@ -393,7 +393,7 @@ impl LLMProvider for OpenAIProvider {
     }
 
     fn max_tokens(&self) -> u32 {
-        self.max_tokens.unwrap_or(16000)
+        self.max_tokens.unwrap_or(32000)
     }
 
     fn temperature(&self) -> f32 {