merge: tui-context-usage-indicator

This commit is contained in:
Keisuke Hirata 2026-05-23 07:15:17 +09:00
commit aa57253e39
16 changed files with 213 additions and 4 deletions

View File

@ -52,6 +52,10 @@ pub struct ModelManifest {
/// `default_capability` → scheme 既定の順で解決される。
#[serde(default, skip_serializing_if = "Option::is_none")]
pub capability: Option<ModelCapability>,
/// モデルのコンテキストウィンドウ上限tokens。カタログ未掲載 / inline
/// モデルでもここで明示 override できる。
#[serde(default, skip_serializing_if = "Option::is_none")]
pub context_window: Option<u64>,
}
impl ModelManifest {
@ -65,6 +69,7 @@ impl ModelManifest {
model_id: upper.model_id.or(self.model_id),
auth: upper.auth.or(self.auth),
capability: upper.capability.or(self.capability),
context_window: upper.context_window.or(self.context_window),
}
}
}

View File

@ -896,6 +896,10 @@ where
// `build_client` がここに到達する前に同じマニフェストで成功している
// ため、カタログ解決も必ず通る。念のため失敗時は "unknown" に落とす。
let resolved = provider::catalog::resolve_model_manifest(&manifest.model).ok();
let context_window = resolved
.as_ref()
.map(|cfg| cfg.context_window)
.unwrap_or(provider::catalog::DEFAULT_CONTEXT_WINDOW);
let (provider_name, model_id) = match resolved {
Some(cfg) => {
let name = match cfg.scheme {
@ -933,6 +937,8 @@ where
model: model_id,
scope_summary: pod.scope_snapshot().summary(),
tools: tool_names,
context_window,
context_tokens: pod.total_tokens().tokens,
}
}
@ -1004,6 +1010,8 @@ mod tests {
model: String::new(),
scope_summary: String::new(),
tools: Vec::new(),
context_window: 200_000,
context_tokens: 0,
},
));
let notify_buffer = NotifyBuffer::new();
@ -1043,6 +1051,8 @@ mod tests {
model: "test".into(),
scope_summary: String::new(),
tools: Vec::new(),
context_window: 200_000,
context_tokens: 0,
},
status: PodStatus::Idle,
})

View File

@ -140,6 +140,8 @@ mod tests {
model: "claude".into(),
scope_summary: String::new(),
tools: Vec::new(),
context_window: 200_000,
context_tokens: 0,
},
)
}

View File

@ -151,6 +151,8 @@ mod tests {
model: "claude".into(),
scope_summary: String::new(),
tools: Vec::new(),
context_window: 200_000,
context_tokens: 0,
}
}

View File

@ -549,6 +549,8 @@ mod tests {
model: "test".into(),
scope_summary: String::new(),
tools: Vec::new(),
context_window: 200_000,
context_tokens: 0,
},
status: PodStatus::Idle,
}

View File

@ -126,6 +126,8 @@ fn empty_snapshot() -> Event {
model: "x".into(),
scope_summary: String::new(),
tools: Vec::new(),
context_window: 200_000,
context_tokens: 0,
},
status: protocol::PodStatus::Idle,
}
@ -198,6 +200,8 @@ fn serve_history(listener: UnixListener, items: Vec<Item>) -> JoinHandle<()> {
model: "x".into(),
scope_summary: String::new(),
tools: Vec::new(),
context_window: 200_000,
context_tokens: 0,
},
status: protocol::PodStatus::Idle,
};

View File

@ -87,6 +87,8 @@ fn empty_snapshot() -> Event {
model: "test".into(),
scope_summary: String::new(),
tools: Vec::new(),
context_window: 200_000,
context_tokens: 0,
},
status: PodStatus::Idle,
}

View File

@ -486,6 +486,12 @@ pub struct Greeting {
pub model: String,
pub scope_summary: String,
pub tools: Vec<String>,
/// Model context window in tokens. Always filled by the Pod greeting.
#[serde(default)]
pub context_window: u64,
/// Estimated current session context tokens at connect time.
#[serde(default)]
pub context_tokens: u64,
}
// ---------------------------------------------------------------------------
@ -873,6 +879,8 @@ mod tests {
model: "claude".into(),
scope_summary: "Writable:\n - /tmp".into(),
tools: vec!["Read".into()],
context_window: 200_000,
context_tokens: 42_000,
},
status: PodStatus::Paused,
};
@ -883,6 +891,8 @@ mod tests {
assert_eq!(parsed["data"]["entries"][0]["kind"], "user_input");
assert_eq!(parsed["data"]["greeting"]["pod_name"], "test");
assert_eq!(parsed["data"]["greeting"]["tools"][0], "Read");
assert_eq!(parsed["data"]["greeting"]["context_window"], 200_000);
assert_eq!(parsed["data"]["greeting"]["context_tokens"], 42_000);
assert_eq!(parsed["data"]["status"], "paused");
}
@ -942,7 +952,13 @@ mod tests {
let json = r#"{"event":"snapshot","data":{"entries":[],"greeting":{"pod_name":"test","cwd":"/tmp","provider":"anthropic","model":"claude","scope_summary":"","tools":[]}}}"#;
let decoded: Event = serde_json::from_str(json).unwrap();
match decoded {
Event::Snapshot { status, .. } => assert_eq!(status, PodStatus::Idle),
Event::Snapshot {
status, greeting, ..
} => {
assert_eq!(status, PodStatus::Idle);
assert_eq!(greeting.context_window, 0);
assert_eq!(greeting.context_tokens, 0);
}
other => panic!("expected Snapshot, got {other:?}"),
}
}

View File

@ -18,3 +18,4 @@
- `AuthRef::None` / `AuthRef::CodexOAuth` の解決
- `Scheme::required_auth()``ResolvedAuth` の妥当性検証(非対応組合せは構築エラー)
- capability は manifest 明示 > model catalog > provider.default_capability > `Scheme::default_capability()` の順で解決
- context window は manifest 明示 > model catalog > provider.default_context_window > builtin fallback の順で解決し、inline model でも `context_window` で override できる

View File

@ -22,6 +22,11 @@ use serde::{Deserialize, Serialize};
const BUILTIN_PROVIDERS: &str = include_str!("../../../resources/providers/builtin.toml");
const BUILTIN_MODELS: &str = include_str!("../../../resources/models/builtin.toml");
/// Conservative fallback used when neither the manifest nor catalogs specify
/// a model context window. Greeting still carries a concrete number, while
/// catalog / manifest metadata can override unknown or inline models.
pub const DEFAULT_CONTEXT_WINDOW: u64 = 200_000;
#[derive(Debug, thiserror::Error)]
pub enum CatalogError {
#[error("failed to read catalog at {path}: {source}")]
@ -92,6 +97,10 @@ pub struct ProviderEntry {
/// 使う。
#[serde(default)]
pub default_capability: Option<ModelCapability>,
/// モデルカタログ未登録モデルで使う既定の context window。省略時は
/// [`DEFAULT_CONTEXT_WINDOW`] を使う。
#[serde(default)]
pub default_context_window: Option<u64>,
}
/// モデルカタログの 1 エントリ。
@ -107,6 +116,10 @@ pub struct ModelEntry {
/// `ProviderEntry::default_capability` にフォールバックする。
#[serde(default)]
pub capability: Option<ModelCapability>,
/// モデル単位の context window。省略時は provider default → builtin
/// fallback にフォールバックする。
#[serde(default)]
pub context_window: Option<u64>,
}
/// 解決済みモデル設定。`build_client` が消費する完成形。
@ -117,6 +130,7 @@ pub struct ModelConfig {
pub model_id: String,
pub auth: AuthRef,
pub capability: Option<ModelCapability>,
pub context_window: u64,
}
#[derive(Debug, Deserialize)]
@ -244,6 +258,8 @@ fn split_ref(s: &str) -> Option<(&str, &str)> {
/// auth は manifest 明示 > provider.auth_hint 由来、capability は
/// manifest 明示 > model catalog > provider.default_capability >
/// `build_client` 側で)`Scheme::default_capability()`。
/// context_window は manifest 明示 > model catalog > provider default >
/// [`DEFAULT_CONTEXT_WINDOW`]。
pub fn resolve_model_manifest(manifest: &ModelManifest) -> Result<ModelConfig, ResolveError> {
let providers = load_providers().map_err(ResolveError::LoadProviders)?;
let models = load_models().map_err(ResolveError::LoadModels)?;
@ -294,12 +310,18 @@ pub fn resolve_with_catalogs(
.and_then(|m| m.capability.clone())
.or_else(|| provider.default_capability.clone())
});
let context_window = manifest
.context_window
.or_else(|| model_entry.and_then(|m| m.context_window))
.or(provider.default_context_window)
.unwrap_or(DEFAULT_CONTEXT_WINDOW);
Ok(ModelConfig {
scheme,
base_url,
model_id,
auth,
capability,
context_window,
})
} else {
let scheme = manifest
@ -319,6 +341,7 @@ pub fn resolve_with_catalogs(
model_id,
auth,
capability: manifest.capability.clone(),
context_window: manifest.context_window.unwrap_or(DEFAULT_CONTEXT_WINDOW),
})
}
}
@ -381,6 +404,20 @@ mod tests {
cfg.capability.is_some(),
"should fall back to provider.default_capability"
);
assert_eq!(cfg.context_window, 200_000);
}
#[test]
fn context_window_manifest_overrides_catalog() {
let providers = load_builtin_providers().unwrap();
let models = load_builtin_models().unwrap();
let manifest = ModelManifest {
ref_: Some("anthropic/claude-sonnet-4-6".into()),
context_window: Some(123_456),
..Default::default()
};
let cfg = resolve_with_catalogs(&manifest, &providers, &models).unwrap();
assert_eq!(cfg.context_window, 123_456);
}
#[test]
@ -461,6 +498,25 @@ mod tests {
assert_eq!(cfg.scheme, SchemeKind::Anthropic);
assert_eq!(cfg.model_id, "claude-sonnet-4-6");
assert!(cfg.capability.is_none(), "no catalog hit for inline-only");
assert_eq!(cfg.context_window, DEFAULT_CONTEXT_WINDOW);
}
#[test]
fn resolve_inline_context_window_override() {
let providers = load_builtin_providers().unwrap();
let models = load_builtin_models().unwrap();
let manifest = ModelManifest {
scheme: Some(SchemeKind::Anthropic),
model_id: Some("claude-sonnet-4-6".into()),
auth: Some(AuthRef::ApiKey {
env: None,
file: Some(PathBuf::from("/tmp/sk")),
}),
context_window: Some(777_000),
..Default::default()
};
let cfg = resolve_with_catalogs(&manifest, &providers, &models).unwrap();
assert_eq!(cfg.context_window, 777_000);
}
#[test]

View File

@ -186,6 +186,7 @@ mod tests {
file: None,
},
capability: None,
context_window: 200_000,
}
}
@ -313,6 +314,7 @@ mod tests {
model_id: "llama3".into(),
auth: AuthRef::None,
capability: None,
context_window: 200_000,
};
assert!(build_client_from_config(&config).is_ok());
}

View File

@ -57,6 +57,10 @@ pub struct App {
/// cache reads excluded). Reset on `RunEnd`.
pub run_upload_tokens: u64,
pub run_output_tokens: u64,
/// Latest session context tokens reported by the Pod. This is the raw
/// `input_tokens` value and is independent from per-run upload totals.
pub session_context_tokens: u64,
pub context_window: u64,
pub turn_index: usize,
pub current_tool: Option<String>,
pub input: InputBuffer,
@ -100,6 +104,8 @@ impl App {
run_requests: 0,
run_upload_tokens: 0,
run_output_tokens: 0,
session_context_tokens: 0,
context_window: 0,
turn_index: 0,
current_tool: None,
input: InputBuffer::new(),
@ -649,6 +655,7 @@ impl App {
output_tokens,
cache_read_input_tokens,
} => {
self.session_context_tokens = input_tokens.unwrap_or(0);
// Subtract the cache-hit portion so a tool loop that
// re-sends the same prefix on every request doesn't
// re-count it. cache_creation stays in (it is full
@ -684,6 +691,7 @@ impl App {
}));
}
Event::CompactDone { new_segment_id } => {
self.session_context_tokens = 0;
if let Some(evt) = self.last_streaming_compact_mut() {
let elapsed_secs = match evt {
CompactEvent::Streaming { started_at } => {
@ -914,6 +922,8 @@ impl App {
/// produced. Followed by `Event::Entry` updates for anything
/// committed after the snapshot.
fn restore_snapshot(&mut self, entries: &[serde_json::Value], greeting: protocol::Greeting) {
self.context_window = greeting.context_window;
self.session_context_tokens = greeting.context_tokens;
self.turn_index = 0;
self.blocks.clear();
self.cache = FileCache::new();
@ -1570,9 +1580,68 @@ mod completion_flow_tests {
model: "test-model".into(),
scope_summary: String::new(),
tools: Vec::new(),
context_window: 200_000,
context_tokens: 0,
}
}
#[test]
fn snapshot_initializes_context_usage() {
let mut app = App::new("test".into());
let mut greeting = test_greeting();
greeting.context_window = 123_000;
greeting.context_tokens = 45_000;
app.handle_pod_event(Event::Snapshot {
entries: Vec::new(),
greeting,
status: PodStatus::Idle,
});
assert_eq!(app.context_window, 123_000);
assert_eq!(app.session_context_tokens, 45_000);
}
#[test]
fn usage_updates_session_context_tokens_without_cache_discount() {
let mut app = App::new("test".into());
app.handle_pod_event(Event::Usage {
input_tokens: Some(42_000),
output_tokens: Some(9),
cache_read_input_tokens: Some(40_000),
});
assert_eq!(app.session_context_tokens, 42_000);
assert_eq!(app.run_upload_tokens, 2_000);
assert_eq!(app.run_output_tokens, 9);
}
#[test]
fn compact_done_resets_session_context_tokens() {
let mut app = App::new("test".into());
app.session_context_tokens = 42_000;
app.handle_pod_event(Event::CompactDone {
new_segment_id: uuid::Uuid::nil(),
});
assert_eq!(app.session_context_tokens, 0);
}
#[test]
fn turn_start_and_run_end_do_not_reset_session_context_tokens() {
let mut app = App::new("test".into());
app.session_context_tokens = 42_000;
app.handle_pod_event(Event::TurnStart { turn: 1 });
app.handle_pod_event(Event::RunEnd {
result: RunResult::Finished,
});
assert_eq!(app.session_context_tokens, 42_000);
}
#[test]
fn live_task_create_updates_task_store() {
let mut app = App::new("test".into());

View File

@ -7,6 +7,7 @@
//! ──────────── separator ──────────
//! status line (1 row)
//! > input area (1 row in Phase 1)
//! actionbar (1 row)
//! ```
//!
//! Every frame we walk the entire `App::blocks` vector, produce styled
@ -78,6 +79,7 @@ pub fn draw(frame: &mut Frame, app: &mut App) {
Constraint::Length(1), // separator
Constraint::Length(1), // status
Constraint::Length(input_height), // input area
Constraint::Length(1), // actionbar
])
.split(area);
@ -88,6 +90,7 @@ pub fn draw(frame: &mut Frame, app: &mut App) {
draw_separator(frame, chunks[3]);
draw_status(frame, app, chunks[4]);
draw_input(frame, &input_render, chunks[5]);
draw_actionbar(frame, app, chunks[6]);
if let Some(state) = app.completion.as_ref().filter(|c| c.is_active()) {
draw_completion_popup(frame, state, chunks[5]);
}
@ -1074,6 +1077,20 @@ fn draw_separator(frame: &mut Frame, area: Rect) {
);
}
fn context_usage_text(app: &App) -> String {
let pct = if app.context_window == 0 {
0
} else {
((app.session_context_tokens as f64 / app.context_window as f64) * 100.0).round() as u64
};
format!(
"{} / {} ({}%)",
fmt_tokens(app.session_context_tokens),
fmt_tokens(app.context_window),
pct
)
}
fn draw_status(frame: &mut Frame, app: &App, area: Rect) {
let conn = if app.connected {
Span::styled("", Style::default().fg(Color::Green))
@ -1124,7 +1141,15 @@ fn draw_status(frame: &mut Frame, app: &App, area: Rect) {
spans.push(Span::styled(" idle", Style::default().fg(Color::DarkGray)));
}
// Right-aligned mode / scroll indicator.
let right_text = context_usage_text(app);
let right_line = Line::from(Span::styled(right_text, Style::default().fg(Color::Gray)))
.alignment(ratatui::layout::Alignment::Right);
frame.render_widget(Paragraph::new(Line::from(spans)), area);
frame.render_widget(Paragraph::new(right_line), area);
}
fn draw_actionbar(frame: &mut Frame, app: &App, area: Rect) {
let mut right: Vec<Span<'static>> = Vec::new();
if !app.scroll.follow_tail {
right.push(Span::styled(
@ -1137,8 +1162,6 @@ fn draw_status(frame: &mut Frame, app: &App, area: Rect) {
Style::default().fg(Color::DarkGray),
));
let right_line = Line::from(right).alignment(ratatui::layout::Alignment::Right);
frame.render_widget(Paragraph::new(Line::from(spans)), area);
frame.render_widget(Paragraph::new(right_line), area);
}

View File

@ -6,3 +6,5 @@ status |● insomnia idle 42.1k / 200k (21%)
input |>
actionbar | ↑ scrolled [normal]
```
status 右端は常に session context usage を `<tokens> / <window> (<pct>%)` 形式で表示する。mode / scrolled などの操作状態は actionbar に寄せる。

View File

@ -2,42 +2,51 @@
[[model]]
id = "claude-sonnet-4-6"
provider = "anthropic"
context_window = 200000
[[model]]
id = "claude-sonnet-4-5"
provider = "anthropic"
context_window = 200000
[[model]]
id = "claude-opus-4-1"
provider = "anthropic"
context_window = 200000
# Ollama local (capability is router-ish / ollama handles its own models)
[[model]]
id = "llama3.1"
provider = "ollama-local"
context_window = 128000
[[model]]
id = "qwen2.5-coder"
provider = "ollama-local"
context_window = 128000
# Codex OAuth (ChatGPT backend via Responses API)
[[model]]
id = "gpt-5-codex"
provider = "codex-oauth"
context_window = 400000
capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "effort", vision = true, prompt_caching = { kind = "auto" } }
[[model]]
id = "gpt-5"
provider = "codex-oauth"
context_window = 400000
capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "effort", vision = true, prompt_caching = { kind = "auto" } }
# OpenRouter
[[model]]
id = "anthropic/claude-sonnet-4"
provider = "openrouter"
context_window = 200000
capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "budget_tokens", vision = true, prompt_caching = { kind = "auto" } }
[[model]]
id = "openai/gpt-5"
provider = "openrouter"
context_window = 400000
capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "effort", vision = true, prompt_caching = { kind = "auto" } }

View File

@ -5,6 +5,7 @@ scheme = "anthropic"
base_url = "https://api.anthropic.com"
auth_hint = { kind = "api_key", env = "INSOMNIA_API_KEY_ANTHROPIC" }
default_capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "budget_tokens", vision = true, prompt_caching = { kind = "explicit", max_breakpoints = 4 } }
default_context_window = 200000
[[provider]]
id = "ollama-local"
@ -13,6 +14,7 @@ scheme = "anthropic"
base_url = "http://localhost:11434"
auth_hint = { kind = "none" }
default_capability = { tool_calling = "parallel", structured_output = "json_schema", vision = false, prompt_caching = { kind = "auto" } }
default_context_window = 128000
[[provider]]
id = "codex-oauth"
@ -20,6 +22,7 @@ display_name = "ChatGPT (Codex OAuth)"
scheme = "openai_responses"
auth_hint = { kind = "codex_oauth" }
default_capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "effort", vision = true, prompt_caching = { kind = "auto" } }
default_context_window = 400000
[[provider]]
id = "openrouter"
@ -28,3 +31,4 @@ scheme = "openai_chat"
base_url = "https://openrouter.ai/api/v1"
auth_hint = { kind = "api_key", env = "INSOMNIA_API_KEY_OPENROUTER" }
default_capability = { tool_calling = "parallel", structured_output = "json_schema", vision = true, prompt_caching = { kind = "auto" } }
default_context_window = 200000