refactor(agent): context boundary detection, proactive budget check, and safe compression

Separate context_window from max_tokens — they serve different purposes
(input capacity vs output generation limit). The previous conflation caused
premature summarization or missed compression triggers.

Changes:
- Add context_window field to AgentDefaults config (default: 4x max_tokens)
- Extract boundary-safe truncation helpers (isSafeBoundary, findSafeBoundary)
  into context_budget.go — pure functions with no AgentLoop dependency
- forceCompression: align split to safe boundary so tool-call sequences
  (assistant+ToolCalls → tool results) are never torn apart
- summarizeSession: use findSafeBoundary instead of hardcoded keep-last-4
- estimateTokens: count ToolCalls arguments and ToolCallID metadata,
  not just Content — fixes systematic undercounting in tool-heavy sessions
- Add proactive context budget check before LLM call in runAgentLoop,
  preventing 400 context-length errors instead of reacting to them
- Add estimateToolDefsTokens for tool definition token cost

Closes #556, closes #665
Ref #1439

pkg/agent/instance.go

@@ -127,6 +127,17 @@ func NewAgentInstance(
 		maxTokens = 8192
 	}
 
+	contextWindow := defaults.ContextWindow
+	if contextWindow == 0 {
+		// Default heuristic: 4x the output token limit.
+		// Most models have context windows well above their output limits
+		// (e.g., GPT-4o 128k ctx / 16k out, Claude 200k ctx / 8k out).
+		// 4x is a conservative lower bound that avoids premature
+		// summarization while remaining safe — the reactive
+		// forceCompression handles any overshoot.
+		contextWindow = maxTokens * 4
+	}
+
 	temperature := 0.7
 	if defaults.Temperature != nil {
 		temperature = *defaults.Temperature
@@ -224,7 +235,7 @@ func NewAgentInstance(
 		MaxTokens:                 maxTokens,
 		Temperature:               temperature,
 		ThinkingLevel:             thinkingLevel,
-		ContextWindow:             maxTokens,
+		ContextWindow:             contextWindow,
 		SummarizeMessageThreshold: summarizeMessageThreshold,
 		SummarizeTokenPercent:     summarizeTokenPercent,
 		Provider:                  provider,