feat(api): compress old tool_result content for small-context providers (#801)

* feat(api): compress old tool_result content for small-context providers

Adds a shim-layer pass that tiers tool_result content by age on
providers
  with small effective context windows (Copilot gpt-4o 128k, Mistral,
  Ollama). Recent turns remain full; mid-tier results are truncated to
2k
  chars; older results are replaced with a stub that preserves tool name
  and arguments so the model can re-invoke if needed.

  Tier sizes auto-tune via getEffectiveContextWindowSize, same
calculation
  used by auto-compact. Reuses COMPACTABLE_TOOLS and
  TOOL_RESULT_CLEARED_MESSAGE to complement (not duplicate)
microCompact.
  Configurable via /config toolHistoryCompressionEnabled.

  Addresses active-session context accumulation on Copilot where
  microCompact's time-based trigger never fires, which surfaces as
  "tools appearing in a loop" and prompt_too_long errors after ~15
turns.

* fix: config tool history

src/services/api/openaiShim.ts

@@ -46,6 +46,7 @@ import {
   type AnthropicUsage,
   type ShimCreateParams,
 } from './codexShim.js'
+import { compressToolHistory } from './compressToolHistory.js'
 import { fetchWithProxyRetry } from './fetchWithProxyRetry.js'
 import {
   getLocalProviderRetryBaseUrls,
@@ -1299,14 +1300,15 @@ class OpenAIShimMessages {
     params: ShimCreateParams,
     options?: { signal?: AbortSignal; headers?: Record<string, string> },
   ): Promise<Response> {
-    const openaiMessages = convertMessages(
+    const compressedMessages = compressToolHistory(
       params.messages as Array<{
         role: string
         message?: { role?: string; content?: unknown }
         content?: unknown
       }>,
-      params.system,
+      request.resolvedModel,
     )
+    const openaiMessages = convertMessages(compressedMessages, params.system)
 
     const body: Record<string, unknown> = {
       model: request.resolvedModel,