feat: surface Copilot usage and quota data across the UI

Add three layers of usage visibility:

- ChatPane footer: premium request count, AIU consumed, and quota
  remaining below the existing context-window bar
- Settings / CopilotStatusCard: on-demand account quota section with
  progress bars, overage indicators, and reset dates fetched via
  the new get-quota sidecar command
- Activity Panel: per-agent token/cost/duration totals on each agent
  row and a Session Usage summary section between agents and timeline

Backend (sidecar):
- New get-quota command using SDK account.getQuota RPC
- New assistant-usage turn-scoped event from SDK assistant.usage
- QuotaSnapshotMapper for both typed and untyped SDK quota payloads
- DTOs: GetQuotaCommandDto, QuotaSnapshotDto, AccountQuotaResultEventDto,
  AssistantUsageEventDto

Frontend:
- Shared types: AssistantUsageEvent, QuotaSnapshot, GetQuotaCommand
- IPC bridge: getQuota channel, assistant-usage event dispatch
- State: SessionRequestUsageMap accumulator with per-agent breakdown
- 8 new tests for accumulator logic and formatting helpers

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
David Kaya
2026-03-29 00:46:09 +01:00
co-authored by Copilot
parent 48efbf36f9
commit 92832c6116
26 changed files with 978 additions and 18 deletions
+5 -1
View File
@@ -200,6 +200,7 @@ The integrated terminal uses the same boundary. The renderer never opens a shell
This is a structured stdio protocol used for:
- capability discovery
- on-demand account quota lookup
- pattern validation
- run execution
- streaming partial output
@@ -212,12 +213,15 @@ The protocol also carries **turn-scoped lifecycle events** alongside output delt
- **Sub-agent events**: started, completed, failed, selected, deselected — surfaced when custom agents are defined
- **Skill invocation events**: emitted when an agent-side skill is triggered
- **Hook lifecycle events**: start and end of configured project hook commands discovered from `.github/hooks/*.json`; Aryx suppresses the SDK's built-in no-op hook chatter so the UI only sees meaningful hook activity
- **Assistant usage events**: per-LLM-call tokens, cost, AIU, and quota snapshots from the Copilot SDK's `assistant.usage` stream
- **Session compaction events**: start and complete, with token-reduction metrics when infinite sessions trigger context trimming
- **Session usage events**: current token count and context-window limit for usage-bar rendering
- **Session usage events**: current token count and context-window limit from `session.usage_info` for context-bar rendering
- **Pending-messages-modified events**: emitted when mid-turn steering changes the pending message queue
These events flow through a single `onTurnScopedEvent` callback on the `runTurn` command, avoiding per-event-type callback proliferation. The main process maps each event to a `SessionEventRecord` and pushes it to the renderer, where lightweight state maps (activity, usage, turn-event log) consume them without touching the persisted workspace.
The same boundary also supports server-scoped sidecar commands that do not require a live Copilot session. The new `get-quota` command uses the SDK's `account.getQuota` RPC to fetch account quota snapshots on demand, then returns them as a `quota-result` protocol event followed by the usual `command-complete` sentinel.
For project-backed sessions, the sidecar also discovers GitHub Copilot CLI hook definitions from `.github/hooks/*.json` under the repository root. Those files are parsed and merged once per run bundle, then projected onto the SDK session hook delegates. Hook commands run synchronously in the sidecar through the platform shell, with stdin JSON payloads shaped to match Copilot CLI hook expectations as closely as the SDK allows. Hook failures are logged to stderr and treated as non-fatal diagnostics, while `preToolUse` hook outputs can still deny a tool call before Aryx falls back to its built-in approval policy.
The `run-turn` command now also carries a project-instruction payload derived from scanned repo customization files. The main process composes that payload from repo-level instruction files and merges enabled discovered custom agent profiles into the primary pattern agent's Copilot configuration before sending the command across the stdio boundary. The sidecar then folds those project instructions into the final SDK system message alongside the agent's own instructions and runtime guidance.