fix: prevent infinite auto-compact loop for unknown 3P models (#635) (#636)

- Raise context window fallback from 8k to 128k for unknown OpenAI-compat models.
  The 8k fallback caused effective context (8k minus output reservation) to go
  negative, making auto-compact fire on every single message.
- Add safety floor in getEffectiveContextWindowSize(): effective context is
  always at least reservedTokensForSummary + 13k buffer, ensuring the
  auto-compact threshold stays positive.
- Add missing MiniMax model entries (M2.5, M2.5-highspeed, M2.1, M2.1-highspeed)
  all at 204,800 context / 131,072 max output per MiniMax docs.
- Add tests for MiniMax variants, 128k fallback, and autoCompact floor.

Fixes #635

Co-authored-by: root <root@vm7508.lumadock.com>

src/utils/context.ts

@@ -9,6 +9,11 @@ import { getOpenAIContextWindow, getOpenAIMaxOutputTokens } from './model/openai
 // Model context window size (200k tokens for all models right now)
 export const MODEL_CONTEXT_WINDOW_DEFAULT = 200_000
 
+// Fallback context window for unknown 3P models. Must be large enough that
+// the effective context (this minus output token reservation) stays positive,
+// otherwise auto-compact fires on every message (issue #635).
+export const OPENAI_FALLBACK_CONTEXT_WINDOW = 128_000
+
 // Maximum output tokens for compact operations
 export const COMPACT_MAX_OUTPUT_TOKENS = 20_000
 
@@ -73,8 +78,9 @@ export function getContextWindowForModel(
   }
 
   // OpenAI-compatible provider — use known context windows for the model.
-  // Unknown models get a conservative 8k default so auto-compact triggers
-  // before hitting a hard context_window_exceeded error.
+  // Unknown models get a conservative 128k default. This was previously 8k,
+  // but that caused auto-compact to fire on every turn because the effective
+  // context (8k minus output reservation) became negative (issue #635).
   const isOpenAIProvider =
     isEnvTruthy(process.env.CLAUDE_CODE_USE_OPENAI) ||
     isEnvTruthy(process.env.CLAUDE_CODE_USE_GEMINI) ||
@@ -86,10 +92,10 @@ export function getContextWindowForModel(
       return openaiWindow
     }
     console.error(
-      `[context] Warning: model "${model}" not in context window table — using conservative 8k default. ` +
+      `[context] Warning: model "${model}" not in context window table — using conservative 128k default. ` +
       'Add it to src/utils/model/openaiContextWindows.ts for accurate compaction.',
     )
-    return 8_000
+    return OPENAI_FALLBACK_CONTEXT_WINDOW
   }
 
   const cap = getModelCapability(model)