Raise default agent token budget for reasoning models

The tracker mapping, common-pattern enrichment, and third-party
disambiguation agents default to a small max-tokens budget on the
premise that their final output is tiny structured JSON. On
reasoning models such as the GPT-5 family, reasoning tokens count
against max_tokens, so a small budget is consumed by reasoning and
the JSON is truncated, surfacing as "unexpected end of JSON input".

Raise the defaults to 4096 (1024 -> 4096 for tracker mapping, 512
-> 4096 for disambiguation) to leave headroom for the reasoning
phase. Update the bootstrap builder default, its test, and the
production values example to match.

Signed-off-by: Émile Ré <emile@probo.com>

contrib/helm/charts/probo/values-production.yaml.example

@@ -174,7 +174,7 @@ probo:
   #   provider: "openai"
   #   modelName: "gpt-4o-mini"
   #   temperature: "0.1"
-  #   maxTokens: "1024"
+  #   maxTokens: "4096"
 
   # Tracker mapping worker tuning (optional; seconds for interval/agentTimeout).
   # Keep concurrency modest to stay under OpenAI/Firecrawl limits and the DB pool.