Raise tracker agent max turns to avoid errors

The tracker-mapping and common-pattern enrichment agents ran with
4 and 3 max turns. Those budgets are smaller than the tool-call
rounds their prompts authorize (two/one DB searches plus up to
three web searches) plus the forced structured-output synthesis
turn, so the run loop tripped MaxTurnsExceededError before it
could emit JSON.

Raise the budgets to 10 across every layer that drives them: the
bootstrap env-var defaults, the Helm chart values and production
example, and the in-code fallback. Update the bootstrap test
defaults to match.

Revert the prompt instructions that told the model to reserve a
turn for its final answer; the model cannot reliably count its
remaining turns, so the fix belongs in the turn budget rather
than the prompt text.

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

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

@@ -184,7 +184,7 @@ probo:
   #   maxConcurrency: 3
   #   staleAfter: 600
   #   agentTimeout: 45
-  #   agentMaxTurns: 4
+  #   agentMaxTurns: 10
 
   # Common-pattern enrichment worker tuning (optional; seconds for
   # interval/staleAfter/agentTimeout).
@@ -193,7 +193,7 @@ probo:
   #   maxConcurrency: 2
   #   staleAfter: 600
   #   agentTimeout: 45
-  #   agentMaxTurns: 3
+  #   agentMaxTurns: 10
 
   # OpenTelemetry tracing (optional)
   tracing:

contrib/helm/charts/probo/values.yaml

@@ -285,7 +285,7 @@ probo:
     maxConcurrency: 3
     staleAfter: 600
     agentTimeout: 45
-    agentMaxTurns: 4
+    agentMaxTurns: 10
 
   # Common-pattern enrichment background worker tuning (optional).
   # interval, staleAfter, and agentTimeout are in seconds.
@@ -294,7 +294,7 @@ probo:
     maxConcurrency: 2
     staleAfter: 600
     agentTimeout: 45
-    agentMaxTurns: 3
+    agentMaxTurns: 10
 
   # Custom domains configuration (optional)
   customDomains: