fix(analysis): raise default ANALYSIS_MAX_TOKENS 900 -> 4096

A text-dense page's full analysis JSON exceeded the 900-token output cap,
so the model stopped mid-object (finish_reason: length) and the truncated
response failed to parse ("EOF while parsing a list"). The page image +
prompt are only a few hundred tokens, so a larger output budget still fits
comfortably in an 8k context window. Still overridable via
ANALYSIS_MAX_TOKENS.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

backend/src/config.rs

@@ -113,6 +113,10 @@ pub struct AnalysisConfig {
     /// Whole-job timeout in the worker (`ANALYSIS_JOB_TIMEOUT_SECS`).
     pub job_timeout: Duration,
     /// Output token cap sent as `max_tokens` (`ANALYSIS_MAX_TOKENS`).
+    /// Must be generous enough to hold the full JSON for a text-dense page
+    /// — too low truncates the response mid-object (`finish_reason:
+    /// length`) and the parse fails. The page image + prompt are only a few
+    /// hundred tokens, so a large output budget still fits an 8k window.
     pub max_tokens: u32,
     /// Longest image edge (px) before downscaling (`ANALYSIS_MAX_IMAGE_DIM`).
     pub max_image_dim: u32,
@@ -134,7 +138,7 @@ impl Default for AnalysisConfig {
             api_key: None,
             request_timeout: Duration::from_secs(120),
             job_timeout: Duration::from_secs(180),
-            max_tokens: 900,
+            max_tokens: 4096,
             max_image_dim: 1024,
             max_image_bytes: 8 * 1024 * 1024,
             response_format: ResponseFormat::JsonSchema,