Files
boocode/apps/web/src/api/client.ts
indifferentketchup 4e6a8389ef v1.13.10: per-tool token cost accounting (rolling 100-call view)
Surfaces per-tool prompt/completion-token rolling averages in
AgentPicker for at-a-glance agent-cost hints. Implementation is a
SQL view on top of messages_with_parts plus a read endpoint and
AgentPicker tooltip extension. No new write site; all source data
already lands via the existing tool-phase.ts:94-95 / error-handler.ts:
109-110 / sentinel-summaries.ts UPDATEs that v1.13.7's includeUsage:
true fix made non-NULL.

(1) schema.sql — new tool_cost_stats view. Window-functions over
messages_with_parts.tool_calls with LATERAL jsonb_array_elements.
Attribution: equal split — multi-tool turn divides tokens N-ways;
the 100-call rolling mean absorbs split noise. Filters: status=
'complete' + metadata.kind NOT IN ('cap_hit','doom_loop') exclude
failed turns and sentinels respectively; tool_calls IS NOT NULL is
defense-in-depth since sentinels are role='system' rows. CREATE OR
REPLACE means schema apply is idempotent.

(2) routes/tools.ts NEW + index.ts wire-in. GET /api/tools/cost_stats
returns { stats: ToolCostStat[] } with mean_prompt_tokens / mean_
completion_tokens computed at read time (sum / n_calls). Sorted by
tool_name ASC. No pagination — ≤30 tools.

(3) __tests__/tool_cost_stats.test.ts NEW — 7 integration tests
keyed off DATABASE_URL env var. Tests skip gracefully when unset
(no-DB default). beforeAll applies the schema via sql.unsafe(read
FileSync(schema.sql)) for self-contained runs. Helper insertAssistant
Turn shared across cases. Covers: empty state, single-tool attribution,
multi-tool equal split, 100-call FIFO window, NULL-tokens exclusion,
parts-authoritative read via messages_with_parts, failed/sentinel
exclusion.

(4) web/api/types.ts + client.ts — ToolCostStat interface + api.tools.
costStats() method binding.

(5) AgentPicker.tsx — fetch costStats on mount, compute per-agent
sum-of-means across whitelisted tools, render muted cost line below
description: "~5.2k prompt / 280 completion · 6/8 tools · last call
3h ago". Skips line entirely when no tool history; preserves existing
native title= for layout backward-compat. formatK/formatAgo colocated.

Tests: 202/202 pass (195 prior + 7 new view-integration). Server +
web tsc clean.

Smoke: schema applied cleanly; GET /api/tools/cost_stats returns
canonical JSON; view + endpoint agree. Single-row result expected
given the v1.13.1-A → v1.13.7 NULL latent regression window; new
traffic populates organically.

Roadmap row at boocode_roadmap.md:114 plus schema row at :474 both
match. View vs table decision documented in handoff_v1.13.10_per_
tool_cost.md (rollback-safe, microsecond-fast at BooCode scale).

~270 LoC across 8 files (5 modified + 3 new).
2026-05-22 14:42:09 +00:00

314 lines
12 KiB
TypeScript

import type {
Project,
AvailableProject,
Session,
Chat,
Message,
ModelInfo,
SidebarResponse,
ListDirResult,
ViewFileResult,
AgentsResponse,
GitMeta,
Skill,
AskUserAnswer,
ToolCostStat,
} from './types';
export class ApiError extends Error {
constructor(
public status: number,
public body: unknown
) {
super(typeof body === 'object' && body && 'error' in body ? String((body as { error: unknown }).error) : `HTTP ${status}`);
}
}
async function request<T>(
path: string,
init: RequestInit = {}
): Promise<T> {
const res = await fetch(path, {
...init,
headers: {
'Content-Type': 'application/json',
...(init.headers ?? {}),
},
});
if (res.status === 204) return undefined as T;
const text = await res.text();
const data = text ? JSON.parse(text) : undefined;
if (!res.ok) throw new ApiError(res.status, data);
return data as T;
}
export const api = {
health: () => request<{ status: string; db: boolean }>('/api/health'),
projects: {
list: (params?: { status?: 'open' | 'archived' }) =>
request<Project[]>(`/api/projects${params?.status ? `?status=${params.status}` : ''}`),
available: () => request<AvailableProject[]>('/api/projects/available'),
add: (body: { path: string; name?: string }) =>
request<Project>('/api/projects', {
method: 'POST',
body: JSON.stringify(body),
}),
update: (
id: string,
body: Partial<Pick<Project, 'name' | 'default_system_prompt' | 'default_web_search_enabled'>>,
) =>
request<Project>(`/api/projects/${id}`, {
method: 'PATCH',
body: JSON.stringify(body),
}),
get: (id: string) => request<Project>(`/api/projects/${id}`),
archive: (id: string) =>
request<void>(`/api/projects/${id}/archive`, { method: 'POST' }),
unarchive: (id: string) =>
request<Project>(`/api/projects/${id}/unarchive`, { method: 'POST' }),
// v1.9: bulk-archive every open session in this project. Server publishes
// one session_archived frame per affected id, so the sidebar reducer
// updates incrementally rather than waiting for a refetch.
archiveAllSessions: (id: string) =>
request<{ archived: number; ids: string[] }>(
`/api/projects/${id}/sessions/archive-all`,
{ method: 'POST' },
),
openSessionsCount: (id: string) =>
request<{ count: number }>(`/api/projects/${id}/sessions/open-count`),
create: (body: {
name: string;
commit_message?: string;
visibility?: 'private' | 'public';
create_gitea_remote?: boolean;
}) =>
request<{
project: Project;
bootstrap: {
folder_created: boolean;
git_initialized: boolean;
first_commit: boolean;
gitea_remote_created: boolean;
gitea_pushed: boolean;
warnings: string[];
};
}>(`/api/projects/create`, {
method: 'POST',
body: JSON.stringify(body),
}),
remove: (id: string) =>
request<void>(`/api/projects/${id}`, { method: 'DELETE' }),
listDir: (id: string, path: string) =>
request<ListDirResult>(`/api/projects/${id}/list_dir?path=${encodeURIComponent(path)}`),
viewFile: (id: string, path: string) =>
request<ViewFileResult>(`/api/projects/${id}/view_file?path=${encodeURIComponent(path)}`),
files: (id: string) =>
request<{ files: string[] }>(`/api/projects/${id}/files`),
git: (id: string) =>
request<GitMeta>(`/api/projects/${id}/git`),
},
sessions: {
listForProject: (projectId: string, status?: 'open' | 'archived') =>
request<Session[]>(`/api/projects/${projectId}/sessions${status ? `?status=${status}` : ''}`),
create: (
projectId: string,
body: { name?: string; model?: string; system_prompt?: string; agent_id?: string | null }
) =>
request<Session>(`/api/projects/${projectId}/sessions`, {
method: 'POST',
body: JSON.stringify(body),
}),
get: (id: string) => request<Session>(`/api/sessions/${id}`),
update: (
id: string,
body: Partial<Pick<Session, 'name' | 'model' | 'system_prompt' | 'agent_id' | 'web_search_enabled'>>
) =>
request<Session>(`/api/sessions/${id}`, {
method: 'PATCH',
body: JSON.stringify(body),
}),
remove: (id: string) =>
request<void>(`/api/sessions/${id}`, { method: 'DELETE' }),
archive: (id: string) =>
request<void>(`/api/sessions/${id}/archive`, { method: 'POST' }),
unarchive: (id: string) =>
request<Session>(`/api/sessions/${id}/unarchive`, { method: 'POST' }),
// v1.9: bulk-archive every open chat in this session. Same pattern as
// archiveAllSessions — server publishes one chat_archived per id.
archiveAllChats: (id: string) =>
request<{ archived: number; ids: string[] }>(
`/api/sessions/${id}/chats/archive-all`,
{ method: 'POST' },
),
openChatsCount: (id: string) =>
request<{ count: number }>(`/api/sessions/${id}/chats/open-count`),
updateWorkspacePanes: (id: string, panes: Session['workspace_panes']) =>
request<Session>(`/api/sessions/${id}/workspace`, {
method: 'PATCH',
body: JSON.stringify({ workspace_panes: panes }),
}),
},
chats: {
listForSession: (sessionId: string, params?: { status?: 'open' | 'archived' }) =>
request<Chat[]>(
`/api/sessions/${sessionId}/chats${params?.status ? `?status=${params.status}` : ''}`
),
create: (sessionId: string, body?: { name?: string }) =>
request<Chat>(`/api/sessions/${sessionId}/chats`, {
method: 'POST',
body: JSON.stringify(body ?? {}),
}),
update: (chatId: string, body: { name: string }) =>
request<Chat>(`/api/chats/${chatId}`, {
method: 'PATCH',
body: JSON.stringify(body),
}),
archive: (chatId: string) =>
request<void>(`/api/chats/${chatId}/archive`, { method: 'POST' }),
unarchive: (chatId: string) =>
request<Chat>(`/api/chats/${chatId}/unarchive`, { method: 'POST' }),
remove: (chatId: string) =>
request<void>(`/api/chats/${chatId}`, { method: 'DELETE' }),
messages: (chatId: string) =>
request<Message[]>(`/api/chats/${chatId}/messages`),
// v1.11: anchored-rolling compaction. POST awaits the LLM call inside
// the route's lifecycle; the new summary row arrives via the 'compacted'
// WS frame (useSessionStream refetches + toasts).
compact: (chatId: string) =>
request<{ ok: true }>(`/api/chats/${chatId}/compact`, { method: 'POST' }),
stop: (chatId: string) =>
request<{ stopped: boolean }>(`/api/chats/${chatId}/stop`, { method: 'POST' }),
discardStale: (chatId: string, messageId: string) =>
request<Message>(`/api/chats/${chatId}/discard_stale`, {
method: 'POST',
body: JSON.stringify({ message_id: messageId }),
}),
forceSend: (chatId: string, content: string) =>
request<{ user_message_id: string; assistant_message_id: string }>(
`/api/chats/${chatId}/force_send`,
{ method: 'POST', body: JSON.stringify({ content }) }
),
// v1.8.2: extend an inference that hit the tool budget. `sentinelMessageId`
// is the cap-hit sentinel message the user clicked Continue on.
continue: (chatId: string, sentinelMessageId: string) =>
request<{ assistant_message_id: string }>(
`/api/chats/${chatId}/continue`,
{ method: 'POST', body: JSON.stringify({ sentinel_message_id: sentinelMessageId }) }
),
fork: (chatId: string, body: { messageId: string; name?: string }) =>
request<Chat>(`/api/chats/${chatId}/fork`, {
method: 'POST',
body: JSON.stringify({ message_id: body.messageId, name: body.name }),
}),
// Batch 9.6: slash-command invocation. Server loads the skill body
// authoritatively (client doesn't get to forge file contents), persists
// a synthetic skill_use tool_use + tool_result + user message + streaming
// assistant, and enqueues inference. Returns all 4 new message IDs.
skillInvoke: (chatId: string, skillName: string, userMessage: string | null) =>
request<{
synth_assistant_id: string;
tool_message_id: string;
user_message_id: string;
assistant_message_id: string;
}>(`/api/chats/${chatId}/skill_invoke`, {
method: 'POST',
body: JSON.stringify({ skill_name: skillName, user_message: userMessage }),
}),
// Batch 9.7: submit answers for a paused ask_user_input call. Server
// validates against the question shape, UPDATEs the pending tool row,
// publishes the deferred tool_result frame, and enqueues the next turn.
answerUserInput: (chatId: string, toolCallId: string, answers: AskUserAnswer[]) =>
request<{ tool_message_id: string; assistant_message_id: string }>(
`/api/chats/${chatId}/answer_user_input`,
{
method: 'POST',
body: JSON.stringify({ tool_call_id: toolCallId, answers }),
},
),
},
messages: {
list: (sessionId: string) =>
request<Message[]>(`/api/sessions/${sessionId}/messages`),
send: (chatId: string, content: string) =>
request<{ user_message_id: string; assistant_message_id: string }>(
`/api/chats/${chatId}/messages`,
{
method: 'POST',
body: JSON.stringify({ content }),
}
),
regenerate: (chatId: string, messageId: string) =>
request<{ assistant_message_id: string }>(
`/api/chats/${chatId}/messages/${messageId}/regenerate`,
{ method: 'POST' }
),
remove: (chatId: string, messageId: string) =>
request<void>(`/api/chats/${chatId}/messages/${messageId}`, {
method: 'DELETE',
}),
},
models: () => request<ModelInfo[]>('/api/models'),
agents: {
list: (projectId: string) =>
request<AgentsResponse>(`/api/projects/${projectId}/agents`),
},
skills: {
list: () => request<{ skills: Skill[] }>('/api/skills'),
},
// v1.13.10: per-tool cost rolling-window stats (last 100 calls per tool,
// equal-split attribution across multi-tool turns). Read endpoint backed by
// the tool_cost_stats view. AgentPicker consumes this for per-agent cost
// hints.
tools: {
costStats: () => request<{ stats: ToolCostStat[] }>('/api/tools/cost_stats'),
},
settings: {
get: () => request<Record<string, unknown>>('/api/settings'),
patch: (body: Record<string, unknown>) =>
request<Record<string, unknown>>('/api/settings', {
method: 'PATCH',
body: JSON.stringify(body),
}),
},
sidebar: {
get: () => request<SidebarResponse>('/api/sidebar'),
},
// v1.10 booterm: REST control plane for terminal panes. WebSocket attach
// lives at /ws/term/sessions/:sid/panes/:pid (handled directly by
// TerminalPane). v1.10.8c: resize moved in-band onto the WebSocket as a
// `{type:"resize",cols,rows}` text frame — the old /resize HTTP endpoint is
// gone, eliminating the race between WS attach and PTY-map registration.
terminals: {
// cols/rows are optional. When passed, booterm sizes the per-pane tmux
// session at creation time so the inner bash (and any TUI it spawns) is
// born with the correct PTY dimensions instead of tmux's 80x24 default.
start: (sessionId: string, paneId: string, cols?: number, rows?: number) =>
request<{ tmux_session: string }>(
`/api/term/sessions/${sessionId}/panes/${paneId}/start`,
{
method: 'POST',
body:
cols !== undefined && rows !== undefined
? JSON.stringify({ cols, rows })
: undefined,
},
),
kill: (sessionId: string, paneId: string) =>
request<{ ok: true }>(
`/api/term/sessions/${sessionId}/panes/${paneId}/kill`,
{ method: 'POST' },
),
},
};