fix: self-calibrate context window from API result event

the stream-json result event carries modelUsage.<model>.contextWindow
which is the actual per-inference active window the model enforces.
for claude-sonnet-4-6 this is 200k even though the full prompt cache
can hold millions of tokens via accumulated cache reads.

with the nix-configured sonnet = 1000000 the proactive compact watermark
sat at 750k and was never reached. agents grew context until prompt_too_long
at ~170k — reactive compact, no checkpoint turn.

changes:
- bus gains api_context_window field seeded from modelUsage.*.contextWindow
  in each turn's result event. authoritative; falls back to env var, then 200k.
- new effective_context_window(bus) helper used by both watermark functions
- compact_watermark (75%) and auto_reset_watermark (50%) call effective_context_window
- context_tokens() docstring clarified: all three token fields (input +
  cache_read + cache_creation) count against the per-inference contextWindow
  limit. the large cache_read values seen in the result event are cumulative
  across all inferences in a turn, not per-inference.
- /api/state context_window_tokens now reflects the calibrated window

closes #129

hive-ag3nt/src/web_ui.rs

@@ -371,10 +371,10 @@ struct StateSnapshot {
     /// in flight). Mutable at runtime via `POST /api/model`.
     model: String,
     /// Effective context-window token budget for the current model.
-    /// Derived from `events::context_window_tokens(&model)` — respects
-    /// per-model and global `HIVE_CONTEXT_WINDOW_TOKENS_*` overrides then
-    /// falls back to model-family heuristic. Consumers (e.g. dashboard
-    /// badge) use this to render the ctx-usage percentage.
+    /// Primary source: API-reported `modelUsage.*.contextWindow` from
+    /// the last result event (authoritative per-inference active window).
+    /// Falls back to `HIVE_CONTEXT_WINDOW_TOKENS_*` env vars, then 200 000.
+    /// Consumers (e.g. dashboard badge) use this to render ctx-usage %.
     context_window_tokens: u64,
     /// Last-inference token usage from the most recent completed
     /// turn — represents the current context-window size at turn-end.
@@ -483,7 +483,10 @@ async fn api_state(headers: HeaderMap, State(state): State<AppState>) -> axum::J
     let inbox = recent_inbox(&state.socket, state.flavor()).await;
     let (turn_state, turn_state_since) = state.bus.state_snapshot();
     let model = state.bus.model();
-    let context_window_tokens = crate::events::context_window_tokens(&model);
+    let context_window_tokens = state
+        .bus
+        .api_context_window()
+        .unwrap_or_else(|| crate::events::context_window_tokens(&model));
     let ctx_usage = state.bus.last_ctx_usage();
     let cost_usage = state.bus.last_cost_usage();
     axum::Json(StateSnapshot {