feat(core): lower default tool-result elision threshold to 2500 chars

Real session data shows ~5k-char skill bodies are the most common
oversized historic result; the 10k default replayed them on every model
call for the life of the session. With the head preview in place the
model retains enough scent to re-load on demand, so the aggressive
default is the right trade. Still tunable via config/context.json.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

apps/x/packages/core/docs/turn-runtime-design.md

@@ -405,7 +405,7 @@ byte-stable across calls (provider prefix caches keep working), and the
 current turn's own messages never pass through the resolver, so in-flight
 tool results and just-captured frames are always sent verbatim. Policy lives
 in `config/context.json` (`elideHistoricToolResults`, default true;
-`elideHistoricToolResultsThresholdChars`, default 10000;
+`elideHistoricToolResultsThresholdChars`, default 2500;
 `elideHistoricImages`, default true; `elideHistoricMiddlePaneContent`,
 default true). The inspect CLI composes through the same decorated resolver.
 

apps/x/packages/core/src/turns/context-elision.ts

@@ -43,9 +43,13 @@ export interface ElisionPolicy {
     middlePaneContent: boolean;
 }
 
+// Threshold rationale: ~2,500 chars ≈ 600 tokens. Observed sessions show
+// skill bodies at ~5k chars are the most common oversized result, so 10k
+// would replay them forever; the head preview plus re-run hint makes the
+// lower cut safe. Tunable via config/context.json.
 export const DEFAULT_ELISION_POLICY: ElisionPolicy = {
     toolResults: true,
-    toolResultThresholdChars: 10_000,
+    toolResultThresholdChars: 2_500,
     images: true,
     middlePaneContent: true,
 };