From 83b7c52ece76b73ee878e9336722572e7d273cab Mon Sep 17 00:00:00 2001
From: r266-tech <r2668940489@gmail.com>
Date: Mon, 22 Jun 2026 09:32:56 +0800
Subject: [PATCH] fix(tui_gateway): don't fall back context_used to cumulative
 session_total_tokens

_get_usage substituted the cumulative lifetime session_total_tokens into
the current-window context_used when an external context engine did not
report last_prompt_tokens, producing impossible status-bar readings
(e.g. 1.9m/120k clamped to 100%). Populate context_used/percent only
from a real current occupancy; leave the gauge unset otherwise. The
built-in compressor always reports last_prompt_tokens, so it's unaffected.

Fixes #50421.
---
 tests/test_tui_gateway_server.py | 39 ++++++++++++++++++++++++++++++++
 tui_gateway/server.py            | 21 +++++++++++++----
 2 files changed, 56 insertions(+), 4 deletions(-)

diff --git a/tests/test_tui_gateway_server.py b/tests/test_tui_gateway_server.py
index 2487e6b95e4..7b4cb62efc1 100644
--- a/tests/test_tui_gateway_server.py
+++ b/tests/test_tui_gateway_server.py
@@ -8474,3 +8474,42 @@ class TestResolveRuntimeWithFallback:
 
         assert agent.model == "gpt-5.5"
         assert captured["provider"] == "deepseek"
+
+
+def test_get_usage_does_not_substitute_cumulative_total_for_context_used():
+    """An external context engine that does not report last_prompt_tokens must
+    not have the cumulative lifetime session_total_tokens shown as its current
+    context occupancy — that substitution produced impossible 1.9m/120k (100%)
+    status-bar readings (#50421). With no real current occupancy known,
+    context_used/percent stay unset rather than wrong."""
+    agent = types.SimpleNamespace(
+        model="test-model",
+        session_total_tokens=1_900_000,
+        context_compressor=types.SimpleNamespace(
+            last_prompt_tokens=0,
+            context_length=120_000,
+            compression_count=0,
+        ),
+    )
+    usage = server._get_usage(agent)
+    assert usage.get("context_used") != 1_900_000
+    assert "context_used" not in usage
+    assert "context_percent" not in usage
+
+
+def test_get_usage_reports_real_current_occupancy():
+    """When the compressor reports a real current prompt size, context_used is
+    that value (not the cumulative total) and the percent is sane."""
+    agent = types.SimpleNamespace(
+        model="test-model",
+        session_total_tokens=1_900_000,
+        context_compressor=types.SimpleNamespace(
+            last_prompt_tokens=60_000,
+            context_length=120_000,
+            compression_count=2,
+        ),
+    )
+    usage = server._get_usage(agent)
+    assert usage["context_used"] == 60_000
+    assert usage["context_max"] == 120_000
+    assert usage["context_percent"] == 50
diff --git a/tui_gateway/server.py b/tui_gateway/server.py
index 6c39b3a66f4..bfdded9dff3 100644
--- a/tui_gateway/server.py
+++ b/tui_gateway/server.py
@@ -2964,12 +2964,25 @@ def _get_usage(agent) -> dict:
     }
     comp = getattr(agent, "context_compressor", None)
     if comp:
-        ctx_used = getattr(comp, "last_prompt_tokens", 0) or usage["total"] or 0
+        # context_used is the *current-window* occupancy. Do NOT fall back to
+        # usage["total"] (cumulative lifetime session_total_tokens): for an
+        # external context engine that doesn't report last_prompt_tokens that
+        # substitution showed lifetime totals as the live context fill, yielding
+        # impossible readings such as 1.9m/120k clamped to 100% (#50421).
+        #
+        # Per the issue, populate context_used/percent only from a *real*
+        # current-occupancy value and "leave it unknown otherwise" — so a falsy
+        # last_prompt_tokens (0 or missing, i.e. an engine that doesn't track
+        # per-window occupancy) intentionally emits no gauge rather than a
+        # fabricated 0% or the old cumulative reading. The built-in compressor
+        # always reports a real last_prompt_tokens once a turn runs, so it is
+        # unaffected.
+        last_prompt = getattr(comp, "last_prompt_tokens", 0) or 0
         ctx_max = getattr(comp, "context_length", 0) or 0
-        if ctx_max:
-            usage["context_used"] = ctx_used
+        if ctx_max and last_prompt:
+            usage["context_used"] = last_prompt
             usage["context_max"] = ctx_max
-            usage["context_percent"] = max(0, min(100, round(ctx_used / ctx_max * 100)))
+            usage["context_percent"] = max(0, min(100, round(last_prompt / ctx_max * 100)))
         usage["compressions"] = getattr(comp, "compression_count", 0) or 0
     # Live count of background/async subagents still running (delegate_task
     # batches + background single delegations). Mirrors the classic CLI status