feat(task): show the agent's context window in task properties (#19273)

## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - Agents run through a harness (Codex app-server, or Claude through
ACPX), and the runner turns harness events into Paperclip events
> - Both harnesses report how full the model's context window is. Codex
sends `modelContextWindow` with its token usage. Claude sends `used` and
`size` in ACP `usage_update`
> - Paperclip dropped both values. The task view could not show how
close an agent is to compaction, and a compaction left no visible mark
in the task chat
> - This pull request carries the context-window occupancy through the
runner, stores it with the existing usage events, and shows it as a
"Context" row in the task Properties panel
> - It also shows a "Context compacted · 230k → 38k tokens" divider in
the task chat when the agent compacts its context
> - The benefit is that operators can see when a long task is near its
context limit and when the agent lost detail to a compaction

## Linked Issues or Issue Description

Refs #19252 (same pattern: a canonical harness event turned into
task-chat UI). Refs #19267 (status notices; it turns Claude's compaction
banner into a notice, and this PR reads that notice too).

**What existing behavior does this improve?**
The task view shows no context-window information, and a compaction is
invisible in the task chat.

**Subsystem affected**
Runner usage normalization (Rust and TypeScript transport), the PRP
usage schema, a read-only issue API, the task Properties panel and the
task-chat transcript.

**Current behavior**
Codex `modelContextWindow` and ACP `used`/`size` are dropped in the
runner. `context.compacted` always has null sizes, Claude compactions
emit no `context.compacted` event at all, and the live runner turn hides
every marker except "interrupted".

**Proposed behavior**
`usage.reported` carries an optional `context {usedTokens,
windowTokens}`. The task Properties panel shows a Context row ("10% of
258k") with a hover breakdown (tokens used, input and cached input,
output, cost, compactions). The transcript shows a compaction divider,
with sizes from the usage before and after the compaction.

**Reason and benefit**
Operators can see when a long task is close to its context limit, and
they can see where the agent's earlier context was summarized.

**Breaking changes**
None. The new schema field is optional, and the new endpoint is
read-only.

## What Changed

- PRP `usage.schema.json`: add an optional `context {usedTokens,
windowTokens}` object. Regenerate the schema bundle and the protocol
manifest.
- Rust `provider_events.rs`: add `codex_context_usage` (last request
`totalTokens` and `modelContextWindow`) and `acpx_context_usage` (ACP
`used`/`size`). ACPX `usage_update` now sets `context`.
- Rust `provider_backend.rs`: Codex `thread/tokenUsage/updated` sets
`context` on live (non-historical) usage.
- Rust `provider_events.rs`: emit `context.compacted` for the completed
`context_compaction` provider notice that #19267 produces from Claude's
compaction banner. Only this path marks a Claude compaction, so the
server counts each compaction once.
- `runnerd-codex-transport.ts`: `rehydrateRunnerdUsageNotification`
keeps a valid `context` on `tokenUsage`, so it reaches the stored
`item.completed` usage item.
- Server: new `GET /api/issues/:id/context-usage` (issue read access is
required) and `issueContextUsage` service. It reads only the assignee's
current session (the session of its newest usage report), and returns
that session's latest context reading, non-zero totals, cost, and the
count of compactions across all of the session's runs. Added to OpenAPI.
Shared type `IssueContextUsage`.
- DB: migration 0432 adds two partial indexes on `heartbeat_run_events`,
built concurrently. One indexes usage items by run and time. The other
indexes `context.compacted` events by company and session. `EXPLAIN`
shows that both lookups use them.
- UI: new `ContextUsageMeter` (bar, percentage, hover card) and
`IssueContextUsageRow` in the Execution section of Properties. The row
refreshes every 8 s while a run is active, and once more when the run
ends.
- UI transcript: `native-run-events.ts` maps `context.compacted` to a
`context` activity entry with pre/post sizes from neighbouring usage
items. `transcript-adapter.ts` turns it into a new `context_compacted`
marker variant. The live runner turn keeps that marker as its own
timeline row.
- Storybook: `task-context-window.stories.tsx` (Properties panel in a
task, all states, hover breakdowns, divider).

## Verification

- `cargo test -p paperclip-runner-core --lib provider_events` (new
tests: ACPX context, Codex context, banner compaction, notice
compaction)
- `pnpm --filter @paperclipai/paperclip-runner exec vitest run
src/live/runnerd-codex-transport.test.ts`
- `cd ui && npx vitest run src/components/ContextUsageMeter.test.tsx
src/components/transcript src/components/task-chat
src/components/issue-properties`
- `cd server && npx vitest run
src/__tests__/issue-context-usage.test.ts` (embedded Postgres)
- `node scripts/typecheck-low-memory.mjs`, `pnpm check:token-gates`,
`pnpm --filter @paperclipai/paperclip-runner run check:protocol-types`
- Live check on a local worktree instance through the runnerd path:
- A Codex `gpt-5.5` task showed "10% of 258k" (27k of 258k, input 77k
with 49k cached, output 1.1k).
  - A Claude Sonnet 4.6 task showed "17% of 200k" (34k of 200k).
- Storybook: Tasks and conversations / … / Task chat / Context window.
- Not verified live: a real compaction. The divider is covered by unit
tests through the same projector path the task chat uses.

## Risks

- The schema field is optional, and older runners omit it. The UI
renders nothing until a harness reports a window.
- Migration 0432 builds two partial indexes concurrently on
`heartbeat_run_events`, which is a large table. The indexes cover only
usage items and compaction events, so they stay small. They add a little
write overhead to those events.
- Claude in-progress usage rows still record zero tokens with `requests:
1`. The final turn usage is correct. This PR does not change accounting.
- A "Compact now" action is out of scope. It needs a compaction-only run
that does not produce a run result. It will come in a follow-up.

## Model Used

- Claude Opus 5.5 (`claude-opus-5-5`), Anthropic, used through Claude
Code with tool use (shell, file edits, in-app browser for Storybook and
the live instance).

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Opus 5.5 <[email protected]>
This commit is contained in:
DottaandClaude Opus 5.5 authored and GitHub committed 2026-11-05 16:54:27 -06:00
1 parent b61a815d3d
commit bf10bc695a
35 files changed
+1760 -11

No files matched your search

+7
View File
@@ -225,6 +225,13 @@ indexes concurrently and can resume an interrupted build without blocking run
writes for the full build. The indexes add storage and run-write overhead; they
do not change task visibility or secret redaction.
The task Context row reads the agent's latest context-window reading through
two small partial indexes on `heartbeat_run_events`. One index covers only usage
items, by run and time. The other index covers only `context.compacted` events,
by company and normalized session. Migration 0432 builds both indexes
concurrently. A poll therefore reads a few index entries, not a run's full event
history.
The chat wake-notice sweep compares UUID columns directly against guarded,
canonical lowercase UUID payload values. Malformed and noncanonical payloads
still match nothing. The query can use existing primary keys without adding a
+1
View File
@@ -591,6 +591,7 @@ const MIGRATIONS_WITH_TOP_LEVEL_STATEMENTS = new Set([
"0413_tired_kronos.sql",
"0414_closed_edwin_jarvis.sql",
"0419_slippery_impossible_man.sql",
"0432_strong_mole_man.sql",
"0384_funny_adam_warlock.sql",
@@ -0,0 +1,2 @@
CREATE INDEX CONCURRENTLY IF NOT EXISTS "heartbeat_run_events_usage_item_run_idx" ON "heartbeat_run_events" USING btree ("run_id","created_at") WHERE "heartbeat_run_events"."event_type" = 'item.completed' and ("heartbeat_run_events"."payload" -> 'prpEvent' -> 'payload' ->> 'kind') = 'usage';--> statement-breakpoint
CREATE INDEX CONCURRENTLY IF NOT EXISTS "heartbeat_run_events_compaction_session_idx" ON "heartbeat_run_events" USING btree ("company_id",("payload" -> 'prpEvent' ->> 'normalizedSessionId')) WHERE "heartbeat_run_events"."event_type" = 'context.compacted';
@@ -1,6 +1,6 @@
{
"id": "dd860bff-55de-4849-8787-58b9de729258",
"prevId": "a1fcb4c6-40e7-47a6-b3f2-c43cd9bf332b",
"id": "a87278a8-15b3-4187-94a9-f4bb79d8640d",
"prevId": "9fcf29d1-a9a6-4ead-8d43-7e087a2b2b24",
"version": "7",
"dialect": "postgresql",
"tables": {
@@ -713,6 +713,12 @@
"notNull": true,
"default": "'{}'::jsonb"
},
"previous_usage_json": {
"name": "previous_usage_json",
"type": "jsonb",
"primaryKey": false,
"notNull": false
},
"reason": {
"name": "reason",
"type": "text",
@@ -7171,6 +7177,147 @@
"checkConstraints": {},
"isRLSEnabled": false
},
"public.budget_evaluation_work": {
"name": "budget_evaluation_work",
"schema": "",
"columns": {
"id": {
"name": "id",
"type": "uuid",
"primaryKey": true,
"notNull": true,
"default": "gen_random_uuid()"
},
"company_id": {
"name": "company_id",
"type": "uuid",
"primaryKey": false,
"notNull": true
},
"agent_id": {
"name": "agent_id",
"type": "uuid",
"primaryKey": false,
"notNull": false
},
"project_id": {
"name": "project_id",
"type": "uuid",
"primaryKey": false,
"notNull": false
},
"created_at": {
"name": "created_at",
"type": "timestamp with time zone",
"primaryKey": false,
"notNull": true,
"default": "now()"
}
},
"indexes": {
"budget_evaluation_work_company_pending_idx": {
"name": "budget_evaluation_work_company_pending_idx",
"columns": [
{
"expression": "company_id",
"isExpression": false,
"asc": true,
"nulls": "last"
},
{
"expression": "created_at",
"isExpression": false,
"asc": true,
"nulls": "last"
},
{
"expression": "id",
"isExpression": false,
"asc": true,
"nulls": "last"
}
],
"isUnique": false,
"concurrently": false,
"method": "btree",
"with": {}
},
"budget_evaluation_work_agent_pending_idx": {
"name": "budget_evaluation_work_agent_pending_idx",
"columns": [
{
"expression": "company_id",
"isExpression": false,
"asc": true,
"nulls": "last"
},
{
"expression": "agent_id",
"isExpression": false,
"asc": true,
"nulls": "last"
},
{
"expression": "created_at",
"isExpression": false,
"asc": true,
"nulls": "last"
}
],
"isUnique": false,
"concurrently": false,
"method": "btree",
"with": {}
},
"budget_evaluation_work_project_pending_idx": {
"name": "budget_evaluation_work_project_pending_idx",
"columns": [
{
"expression": "company_id",
"isExpression": false,
"asc": true,
"nulls": "last"
},
{
"expression": "project_id",
"isExpression": false,
"asc": true,
"nulls": "last"
},
{
"expression": "created_at",
"isExpression": false,
"asc": true,
"nulls": "last"
}
],
"isUnique": false,
"concurrently": false,
"method": "btree",
"with": {}
}
},
"foreignKeys": {
"budget_evaluation_work_company_id_companies_id_fk": {
"name": "budget_evaluation_work_company_id_companies_id_fk",
"tableFrom": "budget_evaluation_work",
"tableTo": "companies",
"columnsFrom": [
"company_id"
],
"columnsTo": [
"id"
],
"onDelete": "cascade",
"onUpdate": "no action"
}
},
"compositePrimaryKeys": {},
"uniqueConstraints": {},
"policies": {},
"checkConstraints": {},
"isRLSEnabled": false
},
"public.budget_incidents": {
"name": "budget_incidents",
"schema": "",
@@ -7518,6 +7665,13 @@
"notNull": true,
"default": 0
},
"evaluation_version": {
"name": "evaluation_version",
"type": "integer",
"primaryKey": false,
"notNull": true,
"default": 0
},
"created_by_user_id": {
"name": "created_by_user_id",
"type": "text",
@@ -21885,6 +22039,12 @@
"primaryKey": false,
"notNull": false
},
"reported_usage_json": {
"name": "reported_usage_json",
"type": "jsonb",
"primaryKey": false,
"notNull": false
},
"pricing_provenance": {
"name": "pricing_provenance",
"type": "jsonb",
@@ -28957,6 +29117,12 @@
"primaryKey": false,
"notNull": true
},
"admitted_project_ids": {
"name": "admitted_project_ids",
"type": "uuid[]",
"primaryKey": false,
"notNull": false
},
"settlement_id": {
"name": "settlement_id",
"type": "uuid",
@@ -29076,6 +29242,10 @@
"execution_admissions_settlement_check": {
"name": "execution_admissions_settlement_check",
"value": "(\"execution_admissions\".\"settlement_id\" is null) = (\"execution_admissions\".\"settled_at\" is null)"
},
"execution_admissions_project_set_check": {
"name": "execution_admissions_project_set_check",
"value": "case when \"execution_admissions\".\"admitted_project_ids\" is null\n then \"execution_admissions\".\"settled_at\" is not null else array_position(\"execution_admissions\".\"admitted_project_ids\", null) is null and cardinality(\"execution_admissions\".\"admitted_project_ids\") <= 100 end"
}
},
"isRLSEnabled": false
@@ -34016,6 +34186,50 @@
"concurrently": false,
"method": "btree",
"with": {}
},
"heartbeat_run_events_usage_item_run_idx": {
"name": "heartbeat_run_events_usage_item_run_idx",
"columns": [
{
"expression": "run_id",
"isExpression": false,
"asc": true,
"nulls": "last"
},
{
"expression": "created_at",
"isExpression": false,
"asc": true,
"nulls": "last"
}
],
"isUnique": false,
"where": "\"heartbeat_run_events\".\"event_type\" = 'item.completed' and (\"heartbeat_run_events\".\"payload\" -> 'prpEvent' -> 'payload' ->> 'kind') = 'usage'",
"concurrently": false,
"method": "btree",
"with": {}
},
"heartbeat_run_events_compaction_session_idx": {
"name": "heartbeat_run_events_compaction_session_idx",
"columns": [
{
"expression": "company_id",
"isExpression": false,
"asc": true,
"nulls": "last"
},
{
"expression": "(\"payload\" -> 'prpEvent' ->> 'normalizedSessionId')",
"asc": true,
"isExpression": true,
"nulls": "last"
}
],
"isUnique": false,
"where": "\"heartbeat_run_events\".\"event_type\" = 'context.compacted'",
"concurrently": false,
"method": "btree",
"with": {}
}
},
"foreignKeys": {
@@ -44016,6 +44230,133 @@
},
"isRLSEnabled": false
},
"public.native_harness_backups": {
"name": "native_harness_backups",
"schema": "",
"columns": {
"id": {
"name": "id",
"type": "uuid",
"primaryKey": true,
"notNull": true,
"default": "gen_random_uuid()"
},
"company_id": {
"name": "company_id",
"type": "uuid",
"primaryKey": false,
"notNull": true
},
"issue_id": {
"name": "issue_id",
"type": "uuid",
"primaryKey": false,
"notNull": true
},
"run_id": {
"name": "run_id",
"type": "uuid",
"primaryKey": false,
"notNull": true
},
"scope_digest": {
"name": "scope_digest",
"type": "text",
"primaryKey": false,
"notNull": true
},
"manifest_sha256": {
"name": "manifest_sha256",
"type": "text",
"primaryKey": false,
"notNull": true
},
"status": {
"name": "status",
"type": "text",
"primaryKey": false,
"notNull": true,
"default": "'pending'"
},
"reference": {
"name": "reference",
"type": "jsonb",
"primaryKey": false,
"notNull": true
},
"created_at": {
"name": "created_at",
"type": "timestamp with time zone",
"primaryKey": false,
"notNull": true,
"default": "now()"
},
"updated_at": {
"name": "updated_at",
"type": "timestamp with time zone",
"primaryKey": false,
"notNull": true,
"default": "now()"
}
},
"indexes": {
"native_harness_backups_current_idx": {
"name": "native_harness_backups_current_idx",
"columns": [
{
"expression": "company_id",
"isExpression": false,
"asc": true,
"nulls": "last"
},
{
"expression": "scope_digest",
"isExpression": false,
"asc": true,
"nulls": "last"
}
],
"isUnique": true,
"where": "\"native_harness_backups\".\"status\" = 'current'",
"concurrently": false,
"method": "btree",
"with": {}
},
"native_harness_backups_scope_idx": {
"name": "native_harness_backups_scope_idx",
"columns": [
{
"expression": "company_id",
"isExpression": false,
"asc": true,
"nulls": "last"
},
{
"expression": "scope_digest",
"isExpression": false,
"asc": true,
"nulls": "last"
},
{
"expression": "manifest_sha256",
"isExpression": false,
"asc": true,
"nulls": "last"
}
],
"isUnique": false,
"concurrently": false,
"method": "btree",
"with": {}
}
},
"foreignKeys": {},
"compositePrimaryKeys": {},
"uniqueConstraints": {},
"policies": {},
"checkConstraints": {},
"isRLSEnabled": false
},
"public.native_run_finalizations": {
"name": "native_run_finalizations",
"schema": "",
+7
View File
@@ -3011,6 +3011,13 @@
"when": 1793798006496,
"tag": "0431_magenta_vanisher",
"breakpoints": true
},
{
"idx": 432,
"version": "7",
"when": 1793916406980,
"tag": "0432_strong_mole_man",
"breakpoints": true
}
]
}
@@ -46,5 +46,13 @@ export const heartbeatRunEvents = pgTable(
.where(sql`${table.sourceInstanceId} is not null and ${table.sourceSeq} is not null`),
companyRunIdx: index("heartbeat_run_events_company_run_idx").on(table.companyId, table.runId),
companyCreatedIdx: index("heartbeat_run_events_company_created_idx").on(table.companyId, table.createdAt),
// Context-window readings: the few usage items per run, newest first.
usageItemRunIdx: index("heartbeat_run_events_usage_item_run_idx")
.on(table.runId, table.createdAt)
.where(sql`${table.eventType} = 'item.completed' and (${table.payload} -> 'prpEvent' -> 'payload' ->> 'kind') = 'usage'`),
// Compactions counted per agent session across runs.
compactionSessionIdx: index("heartbeat_run_events_compaction_session_idx")
.on(table.companyId, sql`(${table.payload} -> 'prpEvent' ->> 'normalizedSessionId')`)
.where(sql`${table.eventType} = 'context.compacted'`),
}),
);
@@ -145,7 +145,7 @@
{
"path": "schemas/usage.schema.json",
"id": "https://paperclip.dev/schemas/prp/v1/usage.schema.json",
"sha256": "be9609768b224459546b800236045b375448f2cb2cb47ccb337e149e0b016361"
"sha256": "ed06a0b50c311e7d8ac6c6fe53f0178cc37a38b65831531efb53cb35c992319f"
},
{
"path": "schemas/workspace-diff.schema.json",
@@ -78,7 +78,17 @@
},
"additionalProperties": false
},
"runDelta": { "$ref": "#/$defs/measurement" }
"runDelta": { "$ref": "#/$defs/measurement" },
"context": {
"description": "Live context-window occupancy for the provider session after this usage, when the provider reports it.",
"type": "object",
"required": ["usedTokens", "windowTokens"],
"properties": {
"usedTokens": { "type": "integer", "minimum": 0 },
"windowTokens": { "type": "integer", "minimum": 1 }
},
"additionalProperties": false
}
},
"additionalProperties": false,
"$defs": {
@@ -31,7 +31,7 @@ use crate::provider_bridge::{
TOOL_SET_SCHEMA,
};
use crate::provider_events::{
normalize_codex_notification, normalize_codex_notification_in,
codex_context_usage, normalize_codex_notification, normalize_codex_notification_in,
normalized_codex_terminal_event_type, with_terminal_outcome, NormalizedProviderEvent,
};
use crate::stable_identity::{is_stable_id, DURABLE_STABLE_ID_CHARS, SHORT_STABLE_ID_CHARS};
@@ -723,6 +723,11 @@ fn normalize_provider_notification(
.codex_usage
.get_or_insert_with(|| CodexRunUsage::new(true))
.observe(total, historical);
let context = if historical {
None
} else {
codex_context_usage(params)
};
let mut normalized_params = params.clone();
let emit_usage = !historical || (had_baseline && increases_known_usage);
if historical && emit_usage {
@@ -743,6 +748,9 @@ fn normalize_provider_notification(
if event.event_type == "usage.reported" {
event.payload["runDeltaAvailable"] = json!(complete);
event.payload["runDeltaBasis"] = json!("run");
if let Some(context) = &context {
event.payload["context"] = context.clone();
}
}
}
return Ok(events);
@@ -832,6 +832,44 @@ fn measurement(value: &Value) -> Value {
})
}
/// Context-window occupancy from a Codex `thread/tokenUsage/updated` payload.
/// Codex sizes the live context by the most recent request's total tokens.
pub(crate) fn codex_context_usage(params: &Value) -> Option<Value> {
let usage = params.get("tokenUsage").unwrap_or(params);
let window = usage
.get("modelContextWindow")
.and_then(Value::as_u64)
.filter(|value| *value > 0)?;
let last = usage.get("last")?;
let used = last
.get("totalTokens")
.and_then(Value::as_u64)
.or_else(|| {
let input = last.get("inputTokens").and_then(Value::as_u64)?;
Some(
input.saturating_add(
last.get("outputTokens")
.and_then(Value::as_u64)
.unwrap_or(0),
),
)
})?;
Some(json!({"usedTokens": used, "windowTokens": window}))
}
/// Context-window occupancy from an ACP `usage_update` (`used` of `size`).
fn acpx_context_usage(payload: &Value) -> Option<Value> {
let window = payload
.get("size")
.and_then(Value::as_f64)
.filter(|value| value.is_finite() && *value >= 1.0)?;
let used = payload
.get("used")
.and_then(Value::as_f64)
.filter(|value| value.is_finite() && *value >= 0.0)?;
Some(json!({"usedTokens": used.round() as u64, "windowTokens": window.round() as u64}))
}
/// Converts Codex app-server notifications into provider-neutral PRP events.
/// Provider-native envelopes are consumed here and never cross the PRP boundary.
fn provider_performance_spans(params: &Value) -> Vec<Value> {
@@ -1508,7 +1546,10 @@ pub fn normalize_acpx_runtime_event(
AcpxRuntimeEventKind::Plan => stable_id(turn_id, fallback_item_id),
_ => stable_id(string(payload.get("messageId")), fallback_item_id),
};
match kind {
let compaction = matches!(kind, AcpxRuntimeEventKind::ProviderNotice)
.then(|| acpx_compaction_notice_completed(payload, turn_id))
.flatten();
let mut events = match kind {
AcpxRuntimeEventKind::TextDelta => vec![NormalizedProviderEvent {
event_type: "item.delta".to_owned(),
priority: EventPriority::P2,
@@ -1583,6 +1624,48 @@ pub fn normalize_acpx_runtime_event(
true,
)],
AcpxRuntimeEventKind::SemanticResult | AcpxRuntimeEventKind::Done => Vec::new(),
};
events.extend(compaction);
events
}
/// A completed `context_compaction` notice (the sidecar's form of Claude's
/// compaction banner) also marks a context compaction.
fn acpx_compaction_notice_completed(
payload: &Value,
turn_id: &str,
) -> Option<NormalizedProviderEvent> {
if string(payload.get("category")) != "context_compaction" {
return None;
}
let completed = payload
.get("details")
.and_then(Value::as_array)?
.iter()
.any(|detail| {
string(detail.get("name")) == "Phase" && string(detail.get("value")) == "completed"
});
if !completed {
return None;
}
Some(acpx_context_compacted(&stable_id(
&format!("{turn_id}:{}", string(payload.get("noticeKey"))),
"acpx-compaction",
)))
}
fn acpx_context_compacted(compaction_id: &str) -> NormalizedProviderEvent {
NormalizedProviderEvent {
event_type: "context.compacted".to_owned(),
priority: EventPriority::P1,
payload: json!({
"schema": "paperclip.context.compacted.v1",
"compactionId": compaction_id,
"reason": "provider",
"preTokens": Value::Null,
"postTokens": Value::Null,
"sameSession": true,
}),
}
}
@@ -1733,7 +1816,7 @@ fn normalize_acpx_status(
"requests": 1,
"providerCostUsd": if turn_cost { provider_cost } else { 0.0 },
});
let usage = NormalizedProviderEvent {
let mut usage = NormalizedProviderEvent {
event_type: "usage.reported".to_owned(),
priority: EventPriority::P0,
payload: json!({
@@ -1749,6 +1832,9 @@ fn normalize_acpx_status(
"runDelta": run_delta,
}),
};
if let Some(context) = acpx_context_usage(payload) {
usage.payload["context"] = context;
}
// Claude forwards its SDK rate_limit_event on usage_update; the
// sidecar passes only the sanitized `rateLimit` fields.
let rate_limits = payload.get("rateLimit").and_then(|info| {
@@ -2298,6 +2384,86 @@ mod tests {
assert_eq!(cumulative[0].payload["runDelta"]["providerCostUsd"], 0.0);
}
#[test]
fn acpx_usage_carries_context_window_occupancy() {
let usage = normalize_acpx_status(
&json!({"tag": "usage_update", "used": 34076, "size": 200000}),
"item",
"turn-1",
1,
);
assert_eq!(
usage[0].payload["context"],
json!({"usedTokens": 34076, "windowTokens": 200000})
);
for missing in [
json!({"tag": "usage_update", "used": 10}),
json!({"tag": "usage_update", "used": 10, "size": 0}),
] {
let usage = normalize_acpx_status(&missing, "item", "turn-1", 1);
assert!(usage[0].payload.get("context").is_none());
}
}
#[test]
fn codex_context_usage_reads_last_request_and_model_window() {
assert_eq!(
codex_context_usage(&json!({"tokenUsage": {
"total": {"inputTokens": 76682, "outputTokens": 1089},
"last": {"inputTokens": 26000, "outputTokens": 672, "totalTokens": 26672},
"modelContextWindow": 258400,
}})),
Some(json!({"usedTokens": 26672, "windowTokens": 258400}))
);
assert_eq!(
codex_context_usage(&json!({"tokenUsage": {
"last": {"inputTokens": 100, "outputTokens": 20}, "modelContextWindow": 1000,
}})),
Some(json!({"usedTokens": 120, "windowTokens": 1000}))
);
assert_eq!(
codex_context_usage(&json!({"tokenUsage": {"last": {"totalTokens": 5}}})),
None
);
}
#[test]
fn compaction_banner_text_alone_is_not_a_compaction() {
// The sidecar turns Claude's banner into a `context_compaction`
// notice; only that notice marks the compaction, so it is counted once.
let events = normalize_acpx_runtime_event(
AcpxRuntimeEventKind::TextDelta,
&json!({"text": "\n\nCompacting completed."}),
None,
"fallback",
"turn-1",
0,
);
assert_eq!(events.len(), 1);
assert_eq!(events[0].event_type, "item.delta");
}
#[test]
fn completed_compaction_notice_emits_context_compacted() {
let notice = |phase: &str| {
normalize_acpx_runtime_event(
AcpxRuntimeEventKind::ProviderNotice,
&json!({"severity": "info", "category": "context_compaction",
"summary": "Compacting context", "noticeKey": "compaction-1",
"details": [{"name": "Phase", "value": phase}]}),
None,
"fallback",
"turn-1",
0,
)
};
assert_eq!(notice("running").len(), 1);
let completed = notice("completed");
assert_eq!(completed.len(), 2);
assert_eq!(completed[1].event_type, "context.compacted");
assert_eq!(completed[1].payload["compactionId"], "turn-1:compaction-1");
}
#[test]
fn performance_diagnostics_keep_only_bounded_content_free_measurements() {
let mut spans = vec![json!({"name":"private prompt","startedAtMs":1,"endedAtMs":2})];
@@ -3108,6 +3108,20 @@ it("rehydrates normalized usage with the opened driver binding", () => {
});
});
it("keeps reported context-window occupancy on rehydrated usage", () => {
const base = { cumulative: { inputTokens: 10 }, runDelta: { inputTokens: 3 }, runDeltaAvailable: true };
const params = rehydrateRunnerdUsageNotification(
{ ...base, context: { usedTokens: 26672, windowTokens: 258400 } },
"opened-thread-1",
"active-turn-1",
);
expect(params.tokenUsage).toMatchObject({ context: { usedTokens: 26672, windowTokens: 258400 } });
for (const context of [undefined, { usedTokens: -1, windowTokens: 10 }, { usedTokens: 1, windowTokens: 0 }]) {
const rehydrated = rehydrateRunnerdUsageNotification({ ...base, context }, "opened-thread-1", "active-turn-1");
expect(rehydrated.tokenUsage).not.toHaveProperty("context");
}
});
it("rehydrates durable cumulative usage for a cold thread read", () => {
expect(
rehydrateRunnerdThreadTokenUsage({ inputTokens: 12, outputTokens: 3 }),
@@ -1879,10 +1879,21 @@ export function rehydrateRunnerdUsageNotification(
// authority beside the counters so ACPX/managed driver projections and
// durable replay cannot certify an incomplete delta as a free receipt.
runDeltaComplete: rawParams.runDeltaAvailable === true,
...runnerdContextUsage(rawParams.context),
},
};
}
/** Context-window occupancy carried on PRP `usage.reported`, when the provider reported it. */
function runnerdContextUsage(value: unknown): { context?: { usedTokens: number; windowTokens: number } } {
const context = record(value);
const usedTokens = context.usedTokens;
const windowTokens = context.windowTokens;
if (typeof usedTokens !== "number" || !Number.isSafeInteger(usedTokens) || usedTokens < 0) return {};
if (typeof windowTokens !== "number" || !Number.isSafeInteger(windowTokens) || windowTokens < 1) return {};
return { context: { usedTokens, windowTokens } };
}
export function rehydrateRunnerdThreadTokenUsage(
cumulative: unknown,
): { total: Record<string, unknown> } | null {
@@ -3673,6 +3673,25 @@ export const usageSchema = {
},
"runDelta": {
"$ref": "#/$defs/measurement"
},
"context": {
"description": "Live context-window occupancy for the provider session after this usage, when the provider reports it.",
"type": "object",
"required": [
"usedTokens",
"windowTokens"
],
"properties": {
"usedTokens": {
"type": "integer",
"minimum": 0
},
"windowTokens": {
"type": "integer",
"minimum": 1
}
},
"additionalProperties": false
}
},
"additionalProperties": false,
+1
View File
@@ -22,6 +22,7 @@ export {
type RunnerGoalActionRequest,
type RunnerGoalActionAccepted,
} from "./runner-goal.js";
export type { IssueContextUsage } from "./issue-context-usage.js";
export { ADAPTER_AUTH_MISSING_CHECK_CODE } from "./adapter-auth-check-code.js";
export {
CONNECTION_INTENT_AGENT_GUIDANCE,
@@ -0,0 +1,23 @@
/**
* Latest context-window occupancy for the agent session working on a task,
* read from the provider usage the runner recorded for the task's runs.
*/
export interface IssueContextUsage {
runId: string;
agentId: string;
/** Normalized runner session the measurement belongs to. */
sessionId: string | null;
usedTokens: number;
windowTokens: number;
observedAt: string;
/** Session totals when the provider reported non-zero counters. */
totals: {
inputTokens: number;
cachedInputTokens: number;
outputTokens: number;
} | null;
/** Provider-reported session cost in USD, when non-zero. */
costUsd: number | null;
/** Compactions recorded for this session. */
compactions: number;
}
@@ -0,0 +1,98 @@
import { randomUUID } from "node:crypto";
import { afterAll, beforeAll, describe, expect, it } from "vitest";
import { agents, companies, createDb, heartbeatRunEvents, heartbeatRuns, issues } from "@paperclipai/db";
import { issueContextUsage } from "../services/issue-context-usage.js";
import { getEmbeddedPostgresTestSupport, startEmbeddedPostgresTestDatabase } from "./helpers/embedded-postgres.js";
const support = await getEmbeddedPostgresTestSupport();
const suite = support.supported ? describe : describe.skip;
suite("issue context usage", () => {
let db: ReturnType<typeof createDb>;
let temporaryDb: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>>;
beforeAll(async () => {
temporaryDb = await startEmbeddedPostgresTestDatabase("issue-context-usage-");
db = createDb(temporaryDb.connectionString);
}, 60_000);
afterAll(async () => { await temporaryDb?.cleanup(); });
function prp(runId: string, sessionId: string, eventType: string, payload: Record<string, unknown>) {
return { prpEvent: { schema: "paperclip.prp.event.v1", runId, normalizedSessionId: sessionId, eventType, payload } };
}
it("returns the latest reported context window and counts the session's compactions", async () => {
const companyId = randomUUID(), agentId = randomUUID(), issueId = randomUUID(), otherIssueId = randomUUID();
await db.insert(companies).values({ id: companyId, name: "Context fixture", issuePrefix: `X${companyId.slice(0, 6)}` });
await db.insert(agents).values({ id: agentId, companyId, name: "Codie", role: "engineer", status: "idle", adapterType: "codex_local" });
await db.insert(issues).values([
{ id: issueId, companyId, title: "Context", status: "in_progress", assigneeAgentId: agentId },
{ id: otherIssueId, companyId, title: "Other", status: "in_progress", assigneeAgentId: agentId },
]);
expect(await issueContextUsage(db, companyId, { id: issueId, assigneeAgentId: agentId })).toBeNull();
const runId = randomUUID(), otherRunId = randomUUID();
await db.insert(heartbeatRuns).values([
{ id: runId, companyId, agentId, scopeKind: "issue", issueId, status: "running" },
{ id: otherRunId, companyId, agentId, scopeKind: "issue", issueId: otherIssueId, status: "running" },
]);
const usage = (usedTokens: number, total = { inputTokens: 76_682, cacheReadTokens: 48_896, outputTokens: 1_089 }) => ({
kind: "usage",
usage: { total, runDelta: total, context: { usedTokens, windowTokens: 258_400 } },
});
const base = { companyId, agentId, stream: "system" as const, level: "info" as const };
await db.insert(heartbeatRunEvents).values([
{ ...base, runId, seq: 1, eventType: "item.completed", payload: prp(runId, "session-a", "item.completed", usage(229_500)),
createdAt: new Date("2026-11-05T10:00:00Z") },
{ ...base, runId, seq: 2, eventType: "context.compacted", payload: prp(runId, "session-a", "context.compacted", {
schema: "paperclip.context.compacted.v1", compactionId: "c-1" }), createdAt: new Date("2026-11-05T10:00:01Z") },
{ ...base, runId, seq: 3, eventType: "item.completed", payload: prp(runId, "session-a", "item.completed", usage(38_200)),
createdAt: new Date("2026-11-05T10:00:02Z") },
{ ...base, runId, seq: 4, eventType: "item.completed", payload: prp(runId, "session-a", "item.completed", { kind: "usage", usage: { total: {} } }),
createdAt: new Date("2026-11-05T10:00:03Z") },
{ ...base, runId: otherRunId, seq: 1, eventType: "item.completed", payload: prp(otherRunId, "session-b", "item.completed", usage(5)),
createdAt: new Date("2026-11-05T10:00:04Z") },
]);
const issue = { id: issueId, assigneeAgentId: agentId };
expect(await issueContextUsage(db, companyId, issue)).toMatchObject({
runId,
agentId,
sessionId: "session-a",
usedTokens: 38_200,
windowTokens: 258_400,
totals: { inputTokens: 76_682, cachedInputTokens: 48_896, outputTokens: 1_089 },
costUsd: null,
compactions: 1,
});
expect(await issueContextUsage(db, randomUUID(), issue)).toBeNull();
// Another assignee's session never shows through.
expect(await issueContextUsage(db, companyId, { id: issueId, assigneeAgentId: randomUUID() })).toBeNull();
expect(await issueContextUsage(db, companyId, { id: issueId, assigneeAgentId: null })).toBeNull();
// A newer run that starts a fresh session hides the old session's reading
// until the new session reports its own context.
const freshRunId = randomUUID();
await db.insert(heartbeatRuns).values({ id: freshRunId, companyId, agentId, scopeKind: "issue", issueId, status: "running",
createdAt: new Date("2026-11-05T11:00:00Z") });
await db.insert(heartbeatRunEvents).values({ ...base, runId: freshRunId, seq: 1, eventType: "item.completed",
payload: prp(freshRunId, "session-c", "item.completed", { kind: "usage", usage: { total: {} } }),
createdAt: new Date("2026-11-05T11:00:01Z") });
expect(await issueContextUsage(db, companyId, issue)).toBeNull();
await db.insert(heartbeatRunEvents).values({ ...base, runId: freshRunId, seq: 2, eventType: "item.completed",
payload: prp(freshRunId, "session-c", "item.completed", usage(12_000)), createdAt: new Date("2026-11-05T11:00:02Z") });
expect(await issueContextUsage(db, companyId, issue)).toMatchObject({ sessionId: "session-c", usedTokens: 12_000, compactions: 0 });
// A session reused across more runs than the lookup window still counts
// compactions from its oldest runs.
const later = ["2026-11-05T12:00:00Z", "2026-11-05T13:00:00Z", "2026-11-05T14:00:00Z"];
for (const [index, at] of later.entries()) {
const id = randomUUID();
await db.insert(heartbeatRuns).values({ id, companyId, agentId, scopeKind: "issue", issueId, status: "succeeded", createdAt: new Date(at) });
await db.insert(heartbeatRunEvents).values({ ...base, runId: id, seq: 1, eventType: "item.completed",
payload: prp(id, "session-c", "item.completed", usage(13_000 + index)), createdAt: new Date(at) });
}
await db.insert(heartbeatRunEvents).values({ ...base, runId: freshRunId, seq: 3, eventType: "context.compacted",
payload: prp(freshRunId, "session-c", "context.compacted", { schema: "paperclip.context.compacted.v1", compactionId: "c-2" }),
createdAt: new Date("2026-11-05T11:00:03Z") });
expect(await issueContextUsage(db, companyId, issue)).toMatchObject({ sessionId: "session-c", usedTokens: 13_002, compactions: 1 });
});
});
+8
View File
@@ -10,6 +10,7 @@ import { sanitizeRecord } from "../redaction.js";
import { badRequest, forbidden } from "../errors.js";
import { agentActionAuditService } from "../services/agent-action-audit.js";
import { logActivity } from "../services/activity-log.js";
import { issueContextUsage } from "../services/issue-context-usage.js";
import { canActorReadHeartbeatRun } from "../services/heartbeat-run-privacy.js";
import { issueReadSqlCondition } from "../services/authorization.js";
import { caseActivityReadSqlCondition } from "../services/case-activity-access.js";
@@ -387,6 +388,13 @@ export function activityRoutes(db: Db) {
res.json(result);
});
router.get("/issues/:id/context-usage", async (req, res) => {
const issue = await getAccessibleResource(req, res, resolveIssueByRef(req.params.id as string), "Issue not found");
if (!issue) return;
if (!(await assertIssueReadAllowed(req, res, issue))) return;
res.json(await issueContextUsage(db, issue.companyId, issue));
});
router.get("/heartbeat-runs/:runId/issues", async (req, res) => {
assertAuthenticated(req);
const runId = req.params.runId as string;
+9
View File
@@ -6168,6 +6168,15 @@ registry.registerPath({
responses: { 200: r.ok(), 400: r.badRequest, 401: r.unauthorized, 403: r.forbidden, 404: r.notFound },
});
registry.registerPath({
method: "get",
path: "/api/issues/{id}/context-usage",
tags: ["activity"],
summary: "Latest context-window usage for an issue's agent session",
request: { params: z.object({ id: z.string() }) },
responses: { 200: r.ok(), 401: r.unauthorized, 403: r.forbidden, 404: r.notFound },
});
registry.registerPath({
method: "get",
path: "/api/heartbeat-runs/{runId}/issues",
+116
View File
@@ -0,0 +1,116 @@
import { and, desc, eq, inArray, or, sql } from "drizzle-orm";
import type { Db } from "@paperclipai/db";
import { heartbeatRunEvents, heartbeatRuns } from "@paperclipai/db";
import type { IssueContextUsage } from "@paperclipai/shared";
/**
* Recent runs of the assignee searched for its newest usage report. The
* usage lookups use `heartbeat_run_events_usage_item_run_idx`, so they read
* only the few usage items of these runs.
*/
const RECENT_RUN_LIMIT = 3;
function count(value: unknown): number | null {
const parsed = typeof value === "string" ? Number(value) : value;
return typeof parsed === "number" && Number.isFinite(parsed) && parsed >= 0 ? parsed : null;
}
function record(value: unknown): Record<string, unknown> | null {
return value && typeof value === "object" && !Array.isArray(value) ? value as Record<string, unknown> : null;
}
/** Matches the predicate of `heartbeat_run_events_usage_item_run_idx`. */
const usageItem = sql`${heartbeatRunEvents.eventType} = 'item.completed' and (${heartbeatRunEvents.payload} -> 'prpEvent' -> 'payload' ->> 'kind') = 'usage'`;
/** Matches the key expression of `heartbeat_run_events_compaction_session_idx`. */
const sessionIdSql = sql<string | null>`(${heartbeatRunEvents.payload} -> 'prpEvent' ->> 'normalizedSessionId')`;
/**
* Reads the most recent provider-reported context occupancy for the current
* agent session on a task. The current session is the one behind the
* assignee's newest usage report: after a reassignment or a fresh session,
* older readings are not returned. Returns null until that session reports a
* context window.
*/
export async function issueContextUsage(
db: Db,
companyId: string,
issue: { id: string; assigneeAgentId: string | null },
): Promise<IssueContextUsage | null> {
if (!issue.assigneeAgentId) return null;
const runs = await db
.select({ id: heartbeatRuns.id })
.from(heartbeatRuns)
.where(and(
eq(heartbeatRuns.companyId, companyId),
eq(heartbeatRuns.agentId, issue.assigneeAgentId),
or(eq(heartbeatRuns.issueId, issue.id), eq(heartbeatRuns.nativeIssueId, issue.id)),
))
.orderBy(desc(heartbeatRuns.createdAt), desc(heartbeatRuns.id))
.limit(RECENT_RUN_LIMIT);
if (runs.length === 0) return null;
const runIds = runs.map((run) => run.id);
const recentUsage = and(
eq(heartbeatRunEvents.companyId, companyId),
inArray(heartbeatRunEvents.runId, runIds),
usageItem,
);
// The newest usage report names the current session.
const [current] = await db
.select({ sessionId: sessionIdSql })
.from(heartbeatRunEvents)
.where(recentUsage)
.orderBy(desc(heartbeatRunEvents.createdAt), desc(heartbeatRunEvents.id))
.limit(1);
const sessionId = current?.sessionId ?? null;
if (!sessionId) return null;
const [latest] = await db
.select({
runId: heartbeatRunEvents.runId,
agentId: heartbeatRunEvents.agentId,
createdAt: heartbeatRunEvents.createdAt,
usage: sql<unknown>`${heartbeatRunEvents.payload} -> 'prpEvent' -> 'payload' -> 'usage'`,
})
.from(heartbeatRunEvents)
.where(and(
recentUsage,
sql`${sessionIdSql} = ${sessionId}`,
sql`${heartbeatRunEvents.payload} -> 'prpEvent' -> 'payload' -> 'usage' ? 'context'`,
))
.orderBy(desc(heartbeatRunEvents.createdAt), desc(heartbeatRunEvents.id))
.limit(1);
if (!latest) return null;
const usage = record(latest.usage);
const context = record(usage?.context);
const usedTokens = count(context?.usedTokens);
const windowTokens = count(context?.windowTokens);
if (usedTokens === null || windowTokens === null || windowTokens < 1) return null;
// Every compaction of the session, across all of its runs.
const [compactions] = await db
.select({ count: sql<number>`count(*)::int` })
.from(heartbeatRunEvents)
.where(and(
eq(heartbeatRunEvents.companyId, companyId),
eq(heartbeatRunEvents.eventType, "context.compacted"),
sql`${sessionIdSql} = ${sessionId}`,
));
const total = record(usage?.total);
const inputTokens = count(total?.inputTokens) ?? 0;
const cachedInputTokens = count(total?.cacheReadTokens) ?? count(total?.cachedInputTokens) ?? 0;
const outputTokens = count(total?.outputTokens) ?? 0;
const costUsd = count(total?.providerCostUsd);
return {
runId: latest.runId,
agentId: latest.agentId,
sessionId,
usedTokens,
windowTokens,
observedAt: latest.createdAt.toISOString(),
totals: inputTokens + outputTokens > 0 ? { inputTokens, cachedInputTokens, outputTokens } : null,
costUsd: costUsd && costUsd > 0 ? costUsd : null,
compactions: compactions?.count ?? 0,
};
}
+2
View File
@@ -2,6 +2,7 @@ import type { SetIssueTitle } from "@paperclipai/shared";
import { ISSUE_SUMMARIES_MAX_IDS } from "@paperclipai/shared";
import type { IssueSummary } from "@paperclipai/shared";
import type { ExecutionReconciliation } from "@paperclipai/shared";
import type { IssueContextUsage } from "@paperclipai/shared";
import type {
AcceptedPlanDecompositionSummary,
AskUserQuestionsAnswer,
@@ -370,6 +371,7 @@ export const issuesApi = {
options
? api.get<Issue>(`/issues/${id}`, options)
: api.get<Issue>(`/issues/${id}`),
getContextUsage: (id: string) => api.get<IssueContextUsage | null>(`/issues/${id}/context-usage`),
getRunnerGoal: (id: string, agentId?: string | null) => {
const query = agentId ? `?agentId=${encodeURIComponent(agentId)}` : "";
return api.get<RunnerGoalProjection>(`/issues/${id}/runner-goal${query}`);
@@ -0,0 +1,24 @@
import { describe, expect, it } from "vitest";
import { contextUsageLevel, formatContextTokens } from "./ContextUsageMeter";
describe("contextUsageLevel", () => {
it("is neutral well below compaction", () => {
expect(contextUsageLevel({ usedTokens: 100_000, contextWindow: 272_000, autoCompactTokens: 244_800 })).toBe("normal");
});
it("turns amber within ten points of auto-compaction", () => {
expect(contextUsageLevel({ usedTokens: 229_500, contextWindow: 272_000, autoCompactTokens: 244_800 })).toBe("near");
expect(contextUsageLevel({ usedTokens: 170_000, contextWindow: 200_000 })).toBe("near");
});
it("turns red at 95%", () => {
expect(contextUsageLevel({ usedTokens: 191_300, contextWindow: 200_000 })).toBe("full");
});
});
describe("formatContextTokens", () => {
it("abbreviates token counts", () => {
expect(formatContextTokens(950)).toBe("950");
expect(formatContextTokens(1_240)).toBe("1.2k");
expect(formatContextTokens(258_400)).toBe("258k");
expect(formatContextTokens(1_000_000)).toBe("1M");
});
});
+187
View File
@@ -0,0 +1,187 @@
import { useRef, useState } from "react";
import { cn } from "@/lib/utils";
import { timeAgo } from "@/lib/timeAgo";
import { formatContextTokens } from "@/lib/context-tokens";
import { Popover, PopoverContent, PopoverTrigger } from "@/components/ui/popover";
export { formatContextTokens };
/**
* Latest context-window snapshot for the agent's live session. Built from
* provider usage events (Codex `thread/tokenUsage/updated`, ACP `usage_update`).
*/
export interface ContextUsage {
/** Tokens currently occupying the context window. */
usedTokens: number;
/** Model context window size in tokens. */
contextWindow: number;
/** Token count at which the harness compacts on its own, when known. */
autoCompactTokens?: number | null;
/** Session totals, when the provider reports them. */
totals?: {
inputTokens?: number | null;
cachedInputTokens?: number | null;
outputTokens?: number | null;
reasoningOutputTokens?: number | null;
} | null;
/** Most recent model request, when the provider reports it. */
lastTurn?: { inputTokens?: number | null; outputTokens?: number | null } | null;
costUsd?: number | null;
/** Number of compactions so far in this session. */
compactions?: number;
/** When the provider reported this reading (ISO timestamp). */
observedAt?: string | null;
}
export type ContextUsageLevel = "normal" | "near" | "full";
/** Amber once the context is within reach of auto-compaction, red when nearly full. */
export function contextUsageLevel(usage: ContextUsage): ContextUsageLevel {
const fraction = usage.usedTokens / usage.contextWindow;
if (fraction >= 0.95) return "full";
const threshold = usage.autoCompactTokens && usage.autoCompactTokens > 0
? usage.autoCompactTokens / usage.contextWindow
: 0.9;
return fraction >= threshold - 0.1 ? "near" : "normal";
}
const LEVEL_TEXT: Record<ContextUsageLevel, string> = {
normal: "text-foreground",
near: "text-(--status-agent-paused)",
full: "text-(--status-agent-error)",
};
const LEVEL_FILL: Record<ContextUsageLevel, string> = {
normal: "bg-muted-foreground",
near: "bg-(--status-agent-paused)",
full: "bg-(--status-agent-error)",
};
function Bar({ percent, level, className }: { percent: number; level: ContextUsageLevel; className?: string }) {
return (
<div className={cn("h-1 overflow-hidden rounded-full bg-border", className)}>
<div
className={cn("h-full rounded-full transition-all duration-500", LEVEL_FILL[level])}
style={{ width: `${percent}%` }}
/>
</div>
);
}
function Row({ label, value, muted }: { label: string; value: string; muted?: boolean }) {
return (
<div className="flex items-baseline justify-between gap-4">
<dt className="text-muted-foreground">{label}</dt>
<dd className={cn("font-mono tabular-nums", muted ? "text-muted-foreground" : "text-foreground")}>{value}</dd>
</div>
);
}
function ContextUsageCard({ usage }: { usage: ContextUsage }) {
const percent = Math.min(100, Math.round((usage.usedTokens / usage.contextWindow) * 100));
const level = contextUsageLevel(usage);
const totals = usage.totals;
return (
<div className="flex flex-col">
<div className="flex items-baseline justify-between gap-2">
<span className="font-medium text-foreground">Context window</span>
<span className={cn("font-medium tabular-nums", LEVEL_TEXT[level])}>{percent}%</span>
</div>
<p className="mt-0.5 text-muted-foreground tabular-nums">
{formatContextTokens(usage.usedTokens)} of {formatContextTokens(usage.contextWindow)} tokens
{usage.observedAt ? <> · updated {timeAgo(usage.observedAt)}</> : null}
</p>
<Bar percent={percent} level={level} className="mt-2 w-full" />
{level !== "normal" ? (
<p className={cn("mt-2", LEVEL_TEXT[level])}>
{usage.autoCompactTokens
? `Compacts automatically near ${formatContextTokens(usage.autoCompactTokens)}.`
: "Close to full. The agent will compact its context soon."}
</p>
) : null}
{totals || usage.lastTurn || usage.costUsd != null || usage.compactions ? (
<dl className="mt-3 flex flex-col gap-1 border-t border-border pt-2">
{totals?.inputTokens != null ? (
<Row
label="Input"
value={totals.cachedInputTokens
? `${formatContextTokens(totals.inputTokens)} · ${formatContextTokens(totals.cachedInputTokens)} cached`
: formatContextTokens(totals.inputTokens)}
/>
) : null}
{totals?.outputTokens != null ? <Row label="Output" value={formatContextTokens(totals.outputTokens)} /> : null}
{totals?.reasoningOutputTokens ? (
<Row label="Reasoning" value={formatContextTokens(totals.reasoningOutputTokens)} muted />
) : null}
{usage.lastTurn ? (
<Row
label="Last request"
value={`${formatContextTokens(usage.lastTurn.inputTokens ?? 0)} in · ${formatContextTokens(usage.lastTurn.outputTokens ?? 0)} out`}
muted
/>
) : null}
{usage.costUsd != null ? <Row label="Cost" value={`$${usage.costUsd.toFixed(2)}`} /> : null}
{usage.compactions ? <Row label="Compactions" value={String(usage.compactions)} muted /> : null}
</dl>
) : null}
</div>
);
}
/**
* Context row value for the task Properties panel: a thin fill bar and
* "64% of 272k". Hover or tap opens the token breakdown.
*/
export function ContextUsageMeter({
usage,
defaultOpen = false,
}: {
usage: ContextUsage;
defaultOpen?: boolean;
}) {
const [open, setOpen] = useState(defaultOpen);
const closeTimer = useRef<ReturnType<typeof setTimeout> | null>(null);
const percent = Math.min(100, Math.round((usage.usedTokens / usage.contextWindow) * 100));
const level = contextUsageLevel(usage);
const windowLabel = formatContextTokens(usage.contextWindow);
const show = () => {
if (closeTimer.current) clearTimeout(closeTimer.current);
setOpen(true);
};
// A short grace period lets the pointer travel from the row into the card.
const hide = () => {
if (closeTimer.current) clearTimeout(closeTimer.current);
closeTimer.current = setTimeout(() => setOpen(false), 150);
};
return (
<Popover open={open} onOpenChange={setOpen}>
<PopoverTrigger asChild>
<button
type="button"
aria-label={`Context window: ${percent}% of ${windowLabel} tokens used`}
data-testid="context-usage-meter"
data-level={level}
onMouseEnter={show}
onMouseLeave={hide}
className="-mx-1 flex min-w-0 items-center gap-2 rounded-md px-1 py-0.5 text-sm transition-colors hover:bg-accent/50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring"
>
<Bar percent={percent} level={level} className="w-12 shrink-0" />
<span className={cn("truncate tabular-nums", level === "normal" ? "text-foreground" : LEVEL_TEXT[level])}>
{percent}%
<span className="text-muted-foreground"> of {windowLabel}</span>
</span>
</button>
</PopoverTrigger>
<PopoverContent
side="left"
align="start"
className="w-64 p-3 text-xs"
onOpenAutoFocus={(event) => event.preventDefault()}
onMouseEnter={show}
onMouseLeave={hide}
>
<ContextUsageCard usage={usage} />
</PopoverContent>
</Popover>
);
}
@@ -36,6 +36,7 @@ const mockExecutionWorkspacesApi = vi.hoisted(() => ({
const mockIssuesApi = vi.hoisted(() => ({
list: vi.fn(),
getContextUsage: vi.fn(),
getDocument: vi.fn(),
listAcceptedPlanDecompositions: vi.fn(),
listAttachments: vi.fn(),
@@ -642,6 +643,7 @@ describe("IssueProperties", () => {
mockExecutionWorkspacesApi.list.mockResolvedValue([]);
mockExecutionWorkspacesApi.controlRuntimeCommands.mockReset();
mockIssuesApi.list.mockResolvedValue([]);
mockIssuesApi.getContextUsage.mockResolvedValue(null);
mockIssuesApi.getDocument.mockResolvedValue(null);
mockIssuesApi.listAcceptedPlanDecompositions.mockResolvedValue([]);
mockIssuesApi.listAttachments.mockResolvedValue([]);
@@ -118,6 +118,7 @@ import {
} from "./helpers";
import { PropertyPicker } from "./property-picker";
import { PropertyChip, PropertyRow, PropertySection } from "./primitives";
import { IssueContextUsageRow } from "./context-usage-row";
import {
buildWorkspaceSelectionUpdate,
currentWorkspaceSelection,
@@ -214,6 +215,8 @@ interface IssuePropertiesProps {
documentDeepLink?: IssuePropertiesDocumentDeepLink | null;
/** Render only the Properties body when a parent owns the side-panel tabs. */
sidePanelContentOnly?: boolean;
/** Overrides the fetched Context row (Storybook fixtures); null hides it. */
contextUsage?: import("react").ReactNode;
}
export interface IssuePropertiesDocumentDeepLink {
@@ -252,6 +255,7 @@ export function IssueProperties({
checkingMonitorNow = false,
documentDeepLink,
sidePanelContentOnly = false,
contextUsage,
}: IssuePropertiesProps) {
const policyResult = useExecutionPolicy(issue.executionPolicy);
const policyAvailable = policyResult.success;
@@ -2762,6 +2766,10 @@ export function IssueProperties({
>
{watchdogContent}
</PropertyPicker>
{contextUsage !== undefined
? contextUsage ? <PropertyRow label="Context">{contextUsage}</PropertyRow> : null
: <IssueContextUsageRow issueId={issue.id} assigneeAgentId={issue.assigneeAgentId ?? null} hasActiveRun={hasActiveRun} />}
</PropertySection>
{workspacePickerEligible || hasWorkspaceRuntimeControls || issue.currentExecutionWorkspace?.branchName || issue.currentExecutionWorkspace?.cwd || issue.executionWorkspaceId ? (
@@ -0,0 +1,84 @@
// @vitest-environment jsdom
import { flushSync } from "react-dom";
import { createRoot, type Root } from "react-dom/client";
import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
const api = vi.hoisted(() => ({ getContextUsage: vi.fn() }));
vi.mock("@/api/issues", () => ({ issuesApi: { getContextUsage: api.getContextUsage } }));
import { ApiError } from "@/api/api-error";
import { IssueContextUsageRow } from "./context-usage-row";
async function settle() {
for (let i = 0; i < 8; i++) { await new Promise(resolve => setTimeout(resolve, 0)); flushSync(() => {}); }
}
let root: Root;
let container: HTMLDivElement;
let client: QueryClient;
beforeEach(() => {
vi.resetAllMocks();
container = document.createElement("div");
document.body.append(container);
root = createRoot(container);
client = new QueryClient({ defaultOptions: { queries: { retry: false } } });
});
afterEach(() => {
flushSync(() => root.unmount());
client.clear();
document.body.innerHTML = "";
});
function render(assigneeAgentId: string | null = "agent-1") {
flushSync(() => root.render(
<QueryClientProvider client={client}>
<IssueContextUsageRow issueId="issue-1" assigneeAgentId={assigneeAgentId} hasActiveRun={false} />
</QueryClientProvider>,
));
}
const reading = {
runId: "run-1", agentId: "agent-1", sessionId: "session-1", usedTokens: 26_672, windowTokens: 258_400,
observedAt: new Date().toISOString(), totals: null, costUsd: null, compactions: 0,
};
describe("IssueContextUsageRow", () => {
it("stays hidden until the session reports a context window", async () => {
api.getContextUsage.mockResolvedValue(null);
render(); await settle();
expect(container.textContent).toBe("");
});
it("shows the reading", async () => {
api.getContextUsage.mockResolvedValue(reading);
render(); await settle();
expect(container.textContent).toContain("10%");
expect(container.textContent).toContain("of 258k");
});
it("shows a failed request with a retry that recovers", async () => {
api.getContextUsage
.mockRejectedValueOnce(new ApiError("Internal error", 500, { error: "internal" }))
.mockResolvedValue(reading);
render(); await settle();
const retry = [...container.querySelectorAll("button")].find((button) => button.textContent?.includes("Retry"));
expect(retry).toBeTruthy();
retry!.click(); await settle();
expect(container.textContent).toContain("10%");
});
it("drops the previous assignee's reading after an idle reassignment", async () => {
api.getContextUsage.mockResolvedValueOnce(reading).mockResolvedValueOnce(null);
render("agent-1"); await settle();
expect(container.textContent).toContain("10%");
render("agent-2"); await settle();
expect(api.getContextUsage).toHaveBeenCalledTimes(2);
expect(container.textContent).toBe("");
});
it("keeps the last reading when a refresh fails", async () => {
api.getContextUsage.mockResolvedValueOnce(reading).mockRejectedValue(new ApiError("Internal error", 500, { error: "internal" }));
render(); await settle();
await client.refetchQueries(); await settle();
expect(container.textContent).toContain("10%");
});
});
@@ -0,0 +1,80 @@
import { useEffect, useRef } from "react";
import { useQuery } from "@tanstack/react-query";
import type { IssueContextUsage } from "@paperclipai/shared";
import { issuesApi } from "../../api/issues";
import { queryKeys } from "../../lib/queryKeys";
import { QueryErrorState, useQueryView } from "../QueryView";
import { ContextUsageMeter, type ContextUsage } from "../ContextUsageMeter";
import { PropertyRow } from "./primitives";
/** Refresh cadence while an agent run is reporting usage. */
const ACTIVE_RUN_REFRESH_MS = 8_000;
export function contextUsageFromIssue(value: IssueContextUsage): ContextUsage {
return {
usedTokens: value.usedTokens,
contextWindow: value.windowTokens,
totals: value.totals
? {
inputTokens: value.totals.inputTokens,
cachedInputTokens: value.totals.cachedInputTokens,
outputTokens: value.totals.outputTokens,
}
: null,
costUsd: value.costUsd,
observedAt: value.observedAt,
compactions: value.compactions,
};
}
/**
* Context row for the task Properties panel. Renders nothing until the
* agent's harness has reported a context window for this task. A cached
* reading stays visible through a failed refresh; a failed first load shows
* the shared error state with Retry.
*/
export function IssueContextUsageRow({
issueId,
assigneeAgentId,
hasActiveRun,
}: {
issueId: string;
/** The reading belongs to the assignee's session, so a reassignment refetches it. */
assigneeAgentId: string | null;
hasActiveRun: boolean;
}) {
const query = useQuery({
queryKey: queryKeys.issues.contextUsage(issueId, assigneeAgentId),
queryFn: () => issuesApi.getContextUsage(issueId),
refetchInterval: hasActiveRun ? ACTIVE_RUN_REFRESH_MS : false,
staleTime: hasActiveRun ? 0 : 60_000,
});
const view = useQueryView(query);
// Pick up the final measurement once the run settles.
const wasActive = useRef(hasActiveRun);
const { refetch } = query;
useEffect(() => {
if (wasActive.current && !hasActiveRun) void refetch();
wasActive.current = hasActiveRun;
}, [hasActiveRun, refetch]);
if (view.data) {
return (
<PropertyRow label="Context">
<ContextUsageMeter usage={contextUsageFromIssue(view.data)} />
</PropertyRow>
);
}
if (view.kind !== "error") return null;
return (
<PropertyRow label="Context">
<QueryErrorState
error={view.error}
size="inline"
action="load the context window"
onRetry={view.retry}
retrying={view.isFetching}
/>
</PropertyRow>
);
}
@@ -1,6 +1,6 @@
import { useId, useState } from "react";
import { cn } from "@/lib/utils";
import { ChevronDown, CircleDot, OctagonX, Square, Flag, KeyRound } from "lucide-react";
import { ChevronDown, CircleDot, FoldVertical, OctagonX, Square, Flag, KeyRound } from "lucide-react";
import { useStreamlinedTaskChatPresentation } from "./presentation-mode";
import type { TaskChatMarkerItem } from "./task-chat-model";
import { Button } from "@/components/ui/button";
@@ -11,6 +11,7 @@ const VARIANT_ICON = {
session_start: CircleDot,
interrupted: OctagonX,
turn_boundary: Flag,
context_compacted: FoldVertical,
} as const;
/**
@@ -16,6 +16,7 @@ import { TaskChatSubagentTree } from "./TaskChatSubagentCard";
import { TaskChatRunHealthBanner, partitionRunHealthItems } from "./TaskChatRunHealthBanner";
import { TaskChatProtocolCard } from "./TaskChatProtocolCard";
import { TaskChatPlanPreviewCard } from "./TaskChatPlanPreviewCard";
import { TaskChatMarker } from "./TaskChatMarker";
import { TaskChatShimmerScope, useTaskChatShimmer } from "./TaskChatShimmer";
import {
buildTurnTimelineRows,
@@ -291,6 +292,8 @@ export function TaskChatRunnerTurn({
: "task-chat-plan-preview"
}
/>
) : row.kind === "marker" ? (
<TaskChatMarker item={row} />
) : row.kind === "subagent_group" ? (
<TaskChatSubagentTree subagents={row.subagents} />
) : row.kind === "protocol" ? (
@@ -294,7 +294,7 @@ export interface TaskChatStatusItem {
export interface TaskChatMarkerItem {
id: string;
kind: "marker";
variant: "session_start" | "interrupted" | "turn_boundary";
variant: "session_start" | "interrupted" | "turn_boundary" | "context_compacted";
label: string;
detail?: string;
/** False when the recorded run cannot be retried, even after the chat continues. */
@@ -8,6 +8,7 @@
import { foldApprovedAutoReviews } from "./fold-auto-reviews";
import { isFatalProviderError, isStatusNotice, isStatusNoticePayload, statusNoticeCategory } from "./status-notice-presentation";
import type { TranscriptEntry } from "@/adapters";
import { formatContextTokens } from "@/lib/context-tokens";
import { turnChangesFromEditRows } from "./turn-file-changes";
import type {
TaskChatDiff,
@@ -24,6 +25,7 @@ import type {
TaskChatMessageItem,
TaskChatPlanDocumentItem,
TaskChatRuntimeRequestItem,
TaskChatMarkerItem,
TaskChatSubagent,
TaskChatSubagentGroupItem,
} from "./task-chat-model";
@@ -133,6 +135,30 @@ export function flattenSelfTalk(text: string): string {
.trim();
}
/** "Context compacted · 230k → 38k tokens" divider for a provider compaction. */
export function contextCompactedMarker(
entry: Extract<TranscriptEntry, { kind: "provider_activity" }>,
id: string,
): TaskChatMarkerItem {
const count = (value: unknown) =>
typeof value === "number" && Number.isFinite(value) && value >= 0 ? value : null;
const pre = count(entry.payload.preTokens);
const post = count(entry.payload.postTokens);
const detail = pre !== null && post !== null
? `${formatContextTokens(pre)} → ${formatContextTokens(post)} tokens`
: pre !== null
? `from ${formatContextTokens(pre)} tokens`
: undefined;
return {
id,
kind: "marker",
variant: "context_compacted",
label: "Context compacted",
...(detail ? { detail } : {}),
createdAtIso: entry.ts,
};
}
function diffKind(changeType: string): "add" | "remove" | "context" | "hunk" {
if (changeType === "add") return "add";
if (changeType === "remove") return "remove";
@@ -979,6 +1005,12 @@ export function transcriptToTaskChatItems(
break;
}
case "provider_activity": {
if (entry.eventType === "context.compacted") {
// One entry per compaction; producers may reuse a thread-scoped id.
items.push(contextCompactedMarker(entry, `${runId}:compaction:${String(entry.payload.compactionId ?? "")}:${i}`));
resetInline();
break;
}
// Use producer classification, including the legacy generic Codex
// categories, never message-text matching. The run transcript still
// retains these diagnostics.
@@ -1369,7 +1401,7 @@ export function paperclipRunnerActivityItems(
return normalizedName !== "paperclip_finish";
}
case "marker":
return item.variant === "interrupted";
return item.variant === "interrupted" || item.variant === "context_compacted";
case "protocol":
// Completion is already represented by task state and the final answer.
// Keep its event in the inspector, but omit it from feed rows and counts.
@@ -2061,6 +2093,10 @@ export function buildTurnTimelineRows(
} else if (item.kind === "plan_document") {
current = null;
rows.push(item);
} else if (item.kind === "marker" && item.variant === "context_compacted") {
// A compaction divides the turn, so it closes the current phase.
current = null;
rows.push(item);
} else if (
item.kind === "protocol" &&
item.surface === "provider_activity" &&
@@ -2,7 +2,7 @@ import { readFileSync } from "node:fs";
import { describe, expect, it } from "vitest";
import type { HeartbeatRunEvent } from "@paperclipai/shared";
import { nativeRunEventsToTranscript } from "./native-run-events";
import { paperclipRunnerFinalResponse, settledRunChildren, transcriptToTaskChatItems } from "../task-chat/transcript-adapter";
import { buildTurnTimelineRows, paperclipRunnerFinalResponse, paperclipRunnerTimelineItems, settledRunChildren, transcriptToTaskChatItems } from "../task-chat/transcript-adapter";
const RUN_ID = "10000000-0000-4000-8000-000000000001";
@@ -1300,6 +1300,87 @@ describe("nativeRunEventsToTranscript", () => {
});
});
describe("context compaction", () => {
function usage(seq: number, usedTokens: number) {
return itemEvent(seq, "item.completed", `turn-1:usage:${seq}`, {
kind: "usage",
usage: { total: { inputTokens: 1 }, context: { usedTokens, windowTokens: 258_400 } },
});
}
it("sizes a compaction from the usage reported before and after it", () => {
const transcript = nativeRunEventsToTranscript([
usage(1, 229_500),
event(2, "context.compacted", {
schema: "paperclip.context.compacted.v1",
compactionId: "compaction-1",
reason: "provider",
preTokens: null,
postTokens: null,
sameSession: true,
}),
usage(3, 38_200),
]);
const compaction = transcript.find((entry) => entry.kind === "provider_activity");
expect(compaction).toMatchObject({
eventType: "context.compacted",
payload: { preTokens: 229_500, postTokens: 38_200 },
});
const items = transcriptToTaskChatItems(transcript, { runId: RUN_ID, agentName: "Codex", running: false });
const flat = JSON.stringify(items);
expect(flat).toContain('"variant":"context_compacted"');
expect(flat).toContain("230k → 38k tokens");
// The live runner turn keeps the divider as its own timeline row.
const rows = buildTurnTimelineRows(paperclipRunnerTimelineItems(items), true);
expect(rows).toEqual(
expect.arrayContaining([expect.objectContaining({ kind: "marker", variant: "context_compacted" })]),
);
});
it("keeps every compaction in a run even when the provider reuses its id", () => {
const compacted = (seq: number) => event(seq, "context.compacted", {
schema: "paperclip.context.compacted.v1",
compactionId: "thread-1",
reason: "provider",
preTokens: null,
postTokens: null,
sameSession: true,
});
const transcript = nativeRunEventsToTranscript([
usage(1, 230_000),
compacted(2),
compacted(3),
usage(4, 40_000),
usage(5, 235_000),
compacted(6),
usage(7, 36_000),
]);
const items = transcriptToTaskChatItems(transcript, { runId: RUN_ID, agentName: "Codex", running: false });
const markers = items.filter((item) => item.kind === "marker" && item.variant === "context_compacted");
expect(markers.map((item) => item.kind === "marker" ? item.detail : null)).toEqual([
"230k → 40k tokens",
"235k → 36k tokens",
]);
});
it("keeps the divider when the provider reports no sizes", () => {
const transcript = nativeRunEventsToTranscript([
event(1, "context.compacted", {
schema: "paperclip.context.compacted.v1",
compactionId: "compaction-2",
reason: "provider",
preTokens: null,
postTokens: null,
sameSession: true,
}),
]);
const items = transcriptToTaskChatItems(transcript, { runId: RUN_ID, agentName: "Claude", running: false });
const flat = JSON.stringify(items);
expect(flat).toContain('"label":"Context compacted"');
expect(flat).not.toContain("tokens");
});
});
describe("tool execution facts", () => {
const tool = (seq: number, eventType: string, fields: Record<string, unknown>) =>
event(seq, eventType, {
@@ -582,6 +582,21 @@ function providerActivityPresentation(
};
}
function finiteCount(value: unknown): number | null {
return typeof value === "number" && Number.isFinite(value) && value >= 0 ? value : null;
}
/** Context-window occupancy carried on a usage item, when the provider reported it. */
export function contextUsageFromUsagePayload(
value: unknown,
): { usedTokens: number; windowTokens: number } | null {
const context = record(record(value)?.context);
const usedTokens = finiteCount(context?.usedTokens);
const windowTokens = finiteCount(context?.windowTokens);
if (usedTokens === null || windowTokens === null || windowTokens < 1) return null;
return { usedTokens, windowTokens };
}
/**
* Activity families that render as dedicated task-chat cards. They keep the
* full canonical payload (sources, models, durations) instead of collapsing
@@ -955,6 +970,12 @@ export function nativeRunEventsToTranscript(events: readonly HeartbeatRunEvent[]
}
const itemIdentityById = new Map<string, ItemIdentity>();
// Context occupancy rides on usage items. A compaction divider takes its
// "before" size from the last report and its "after" size from the next.
let latestContextUsedTokens: number | null = null;
let awaitingPostCompaction: Record<string, unknown> | null = null;
let lastCompaction: Record<string, unknown> | null = null;
let usageSinceLastCompaction = false;
const proposalMarkdownById = new Map<string, string>();
const completedProposalIds = new Set<string>();
for (const event of orderedEvents) {
@@ -979,6 +1000,47 @@ export function nativeRunEventsToTranscript(events: readonly HeartbeatRunEvent[]
}
const itemKind = itemIdentity.kind;
if (event.eventType === "item.completed" && payload.kind === "usage") {
const context = contextUsageFromUsagePayload(payload.usage);
if (context) {
usageSinceLastCompaction = true;
if (awaitingPostCompaction && context.usedTokens < (latestContextUsedTokens ?? Infinity)) {
awaitingPostCompaction.postTokens = context.usedTokens;
awaitingPostCompaction = null;
}
latestContextUsedTokens = context.usedTokens;
}
}
if (event.eventType === "context.compacted" && payload.schema === "paperclip.context.compacted.v1") {
// A provider can report the same compaction twice (item start and end)
// with no usage between them. Later compactions always follow usage.
if (
lastCompaction
&& lastCompaction.compactionId === payload.compactionId
&& !usageSinceLastCompaction
) continue;
usageSinceLastCompaction = false;
const compaction: Record<string, unknown> = {
...payload,
preTokens: finiteCount(payload.preTokens) ?? latestContextUsedTokens,
postTokens: finiteCount(payload.postTokens),
};
if (compaction.postTokens === null) awaitingPostCompaction = compaction;
lastCompaction = compaction;
entries.push({
kind: "provider_activity",
ts,
family: "context",
eventType: event.eventType,
status: "completed",
title: "Context compacted",
summary: "Context compacted",
payload: compaction,
});
continue;
}
if (event.eventType === "item.delta" && isAssistantItemKind(itemKind)) {
const value = normalizedItemText(payload);
if (!value || !itemId) continue;
+10
View File
@@ -0,0 +1,10 @@
/** Compact token count for context-window labels: 950, 1.2k, 258k, 1M. */
export function formatContextTokens(value: number): string {
if (value >= 1_000_000) return `${trimDecimal(value / 1_000_000)}M`;
if (value >= 1_000) return value >= 10_000 ? `${Math.round(value / 1_000)}k` : `${trimDecimal(value / 1_000)}k`;
return String(Math.round(value));
}
function trimDecimal(value: number): string {
return value.toFixed(1).replace(/\.0$/, "");
}
+2
View File
@@ -413,6 +413,8 @@ export const queryKeys = {
approvals: (issueId: string) => ["issues", "approvals", issueId] as const,
liveRuns: (issueId: string) => ["issues", "live-runs", issueId] as const,
activeRun: (issueId: string) => ["issues", "active-run", issueId] as const,
contextUsage: (issueId: string, assigneeAgentId: string | null) =>
["issues", "context-usage", issueId, assigneeAgentId] as const,
runnerGoal: (issueId: string, agentId?: string | null) =>
["issues", "runner-goal", issueId, agentId ?? "__effective__"] as const,
workProducts: (issueId: string) =>
@@ -0,0 +1,318 @@
import { useState, type ReactNode } from "react";
import { useQueryClient } from "@tanstack/react-query";
import type { Meta, StoryObj } from "@storybook/react-vite";
import { TaskChatThreadView } from "@/components/task-chat/TaskChatThreadView";
import { TaskChatMarker } from "@/components/task-chat/TaskChatMarker";
import { TaskChatPresentationProvider } from "@/components/task-chat/presentation-mode";
import { ContextUsageMeter, type ContextUsage } from "@/components/ContextUsageMeter";
import { IssueProperties } from "@/components/IssueProperties";
import { ScrollArea } from "@/components/ui/scroll-area";
import { queryKeys } from "@/lib/queryKeys";
import type {
TaskChatItem,
TaskChatMarkerItem,
TaskChatMessageItem,
TaskChatToolItem,
} from "@/components/task-chat/task-chat-model";
import {
storybookAgents,
storybookAuthSession,
storybookCompanies,
storybookIssueLabels,
storybookIssues,
storybookProjects,
} from "../../fixtures/paperclipData";
/** Codex gpt-5 class session: 272k window, auto-compacts around 245k. */
const CODEX_WINDOW = 272_000;
const CODEX_COMPACT = 244_800;
const USAGE = {
fresh: {
usedTokens: 18_400,
contextWindow: CODEX_WINDOW,
autoCompactTokens: CODEX_COMPACT,
totals: { inputTokens: 21_300, cachedInputTokens: 9_800, outputTokens: 1_240 },
lastTurn: { inputTokens: 18_400, outputTokens: 1_240 },
},
working: {
usedTokens: 174_100,
contextWindow: CODEX_WINDOW,
autoCompactTokens: CODEX_COMPACT,
totals: { inputTokens: 1_480_000, cachedInputTokens: 1_310_000, outputTokens: 31_800, reasoningOutputTokens: 12_400 },
lastTurn: { inputTokens: 174_100, outputTokens: 2_150 },
},
nearCompaction: {
usedTokens: 229_500,
contextWindow: CODEX_WINDOW,
autoCompactTokens: CODEX_COMPACT,
totals: { inputTokens: 3_920_000, cachedInputTokens: 3_610_000, outputTokens: 58_200, reasoningOutputTokens: 21_900 },
lastTurn: { inputTokens: 229_500, outputTokens: 1_870 },
},
afterCompaction: {
usedTokens: 38_200,
contextWindow: CODEX_WINDOW,
autoCompactTokens: CODEX_COMPACT,
totals: { inputTokens: 4_310_000, cachedInputTokens: 3_840_000, outputTokens: 63_900, reasoningOutputTokens: 23_100 },
lastTurn: { inputTokens: 38_200, outputTokens: 940 },
compactions: 1,
},
claudeNearlyFull: {
usedTokens: 191_300,
contextWindow: 200_000,
totals: { inputTokens: 2_640_000, cachedInputTokens: 2_410_000, outputTokens: 44_700 },
costUsd: 3.18,
},
claudeWithCost: {
usedTokens: 61_900,
contextWindow: 200_000,
totals: { inputTokens: 412_000, cachedInputTokens: 366_000, outputTokens: 9_300 },
costUsd: 0.47,
},
windowOnly: { usedTokens: 96_000, contextWindow: 200_000 },
} satisfies Record<string, ContextUsage>;
const compactedMarker: TaskChatMarkerItem = {
id: "compacted-1",
kind: "marker",
variant: "context_compacted",
label: "Context compacted",
detail: "230k → 38k tokens",
};
const autoCompactedClaude: TaskChatMarkerItem = {
id: "compacted-claude",
kind: "marker",
variant: "context_compacted",
label: "Context compacted",
detail: "188k → 24k tokens",
};
const unknownSizes: TaskChatMarkerItem = {
id: "compacted-unknown",
kind: "marker",
variant: "context_compacted",
label: "Context compacted",
};
const request: TaskChatMessageItem = {
id: "request",
kind: "message",
author: "human",
authorName: "Alex",
isCurrentUser: true,
text: "Port the billing exporter to the new SDK and keep the CSV output byte-identical.",
timestamp: "2:04 PM",
};
const tool = (id: string, name: string, target: string): TaskChatToolItem => ({
id, kind: "tool", name, target, status: "completed",
});
const progress: TaskChatMessageItem = {
id: "progress",
kind: "message",
author: "agent",
authorName: "Codex",
channel: "progress",
interstitial: true,
text: "Mapped all 41 call sites of the legacy client. Porting the streaming reader next.",
timestamp: "2:19 PM",
};
const afterCompaction: TaskChatMessageItem = {
id: "after",
kind: "message",
author: "agent",
authorName: "Codex",
channel: "progress",
interstitial: true,
text: "Picking up from the summary: streaming reader is ported, batch uploader is next.",
timestamp: "2:31 PM",
};
const THREAD: TaskChatItem[] = [
request,
tool("t1", "Search", "legacyClient\\."),
tool("t2", "Read", "server/src/billing/exporter.ts"),
progress,
tool("t3", "Edit", "server/src/billing/stream-reader.ts"),
tool("t4", "Run", "pnpm vitest billing"),
compactedMarker,
afterCompaction,
tool("t5", "Read", "server/src/billing/batch-uploader.ts"),
];
const companyId = "company-storybook";
const issue = storybookIssues[0]!;
function StorybookData({ children }: { children: ReactNode }) {
const queryClient = useQueryClient();
const [ready] = useState(() => {
queryClient.setQueryData(queryKeys.companies.all, { companies: storybookCompanies, unauthorized: false });
queryClient.setQueryData(queryKeys.auth.session, storybookAuthSession);
queryClient.setQueryData(queryKeys.agents.list(companyId), storybookAgents);
queryClient.setQueryData(queryKeys.projects.list(companyId), storybookProjects);
queryClient.setQueryData(queryKeys.projects.list(companyId, { includeArchived: true }), storybookProjects);
queryClient.setQueryData(queryKeys.issues.list(companyId), storybookIssues);
queryClient.setQueryData(queryKeys.issues.labels(companyId), storybookIssueLabels);
queryClient.setQueryData(queryKeys.issues.liveRuns(issue.id), []);
queryClient.setQueryData(queryKeys.issues.activeRun(issue.id), null);
return true;
});
return ready ? children : null;
}
function PropertiesPane({ usage, defaultOpen }: { usage: ContextUsage; defaultOpen?: boolean }) {
return (
<StorybookData>
<div className="flex h-(--sz-640px) w-80 flex-col overflow-hidden border border-border bg-card">
<div className="border-b border-border px-4 py-2 text-sm font-medium">Properties</div>
<ScrollArea className="flex-1">
<div className="p-4">
<IssueProperties
issue={issue}
childIssues={[]}
onUpdate={() => undefined}
contextUsage={<ContextUsageMeter usage={usage} defaultOpen={defaultOpen} />}
/>
</div>
</ScrollArea>
</div>
</StorybookData>
);
}
function Page({ children, narrow }: { children: ReactNode; narrow?: boolean }) {
return (
<div className="min-h-screen bg-background p-6 text-foreground">
<div className={narrow ? "mx-auto w-full max-w-sm" : "mx-auto w-full max-w-2xl"}>{children}</div>
</div>
);
}
function StateCard({ title, rule, children }: { title: string; rule: string; children: ReactNode }) {
return (
<section className="flex flex-col gap-3">
<div>
<h3 className="text-sm font-semibold">{title}</h3>
<p className="text-xs text-muted-foreground">{rule}</p>
</div>
{children}
</section>
);
}
/** A Properties-style row without the full panel, for comparing states. */
function MeterRow({ usage }: { usage: ContextUsage }) {
return (
<div className="flex w-80 items-center gap-3 rounded-md border border-border bg-card px-4 py-2">
<span className="w-24 shrink-0 text-xs text-muted-foreground">Context</span>
<ContextUsageMeter usage={usage} />
</div>
);
}
function TaskPage() {
return (
<div className="flex min-h-screen gap-6 bg-background p-6 text-foreground">
<div className="min-w-0 flex-1">
<h1 className="mb-4 text-xl font-semibold">Port billing exporter to the new SDK</h1>
<TaskChatPresentationProvider mode="streamlined">
<TaskChatThreadView items={THREAD} scroll={false} />
</TaskChatPresentationProvider>
</div>
<div className="pl-72">
<PropertiesPane usage={USAGE.afterCompaction} />
</div>
</div>
);
}
function AllStates() {
return (
<Page>
<div className="flex flex-col gap-10">
<header>
<h2 className="text-lg font-semibold">Context window</h2>
<p className="text-sm text-muted-foreground">
A Context row in the task&apos;s Properties shows how full the assigned agent&apos;s context window is. Hover
or tap it for the token breakdown. Codex reports usage through{" "}
<code className="font-mono text-xs">thread/tokenUsage/updated</code>, Claude through ACP{" "}
<code className="font-mono text-xs">usage_update</code>.
</p>
</header>
<StateCard title="Fresh session" rule="Neutral bar, percentage and window size.">
<MeterRow usage={USAGE.fresh} />
</StateCard>
<StateCard title="Working" rule="Bar fills as the conversation grows. Still neutral.">
<MeterRow usage={USAGE.working} />
</StateCard>
<StateCard title="Near auto-compaction" rule="Amber within 10 points of the harness's auto-compaction threshold.">
<MeterRow usage={USAGE.nearCompaction} />
</StateCard>
<StateCard title="Nearly full (Claude)" rule="Red at 95% or more.">
<MeterRow usage={USAGE.claudeNearlyFull} />
</StateCard>
<StateCard title="Hidden" rule="No Context row until the agent's harness has reported a context window for this task's session.">
<p className="text-xs text-muted-foreground">(no row)</p>
</StateCard>
<StateCard title="Compaction divider" rule="A transcript rule marks the point where the agent's context was summarized, with before and after sizes when known.">
<div className="flex flex-col gap-3">
<TaskChatMarker item={compactedMarker} />
<TaskChatMarker item={autoCompactedClaude} />
<TaskChatMarker item={unknownSizes} />
</div>
</StateCard>
</div>
</Page>
);
}
function Breakdown({ usage }: { usage: ContextUsage }) {
return (
<div className="flex min-h-screen justify-end bg-background p-6 text-foreground">
<PropertiesPane usage={usage} defaultOpen />
</div>
);
}
const meta = {
id: "product-task-context-window",
title: "Tasks and conversations/Task creation and lifecycle/Product/Task chat/Context window",
component: ContextUsageMeter,
args: { usage: USAGE.working },
parameters: {
layout: "fullscreen",
docs: {
description: {
component:
"Context row in the task Properties panel with a hover breakdown, plus the transcript divider recorded when the agent's context is compacted.",
},
},
paperclip: {
"capabilities": [
"tasks/discussion",
"runs-adapters/runs"
],
"implementation": "production",
"boundary": "fixtures",
"notes": "Renders the context meter inside the production Issue Properties panel and the compaction divider in the production thread view, from fixture usage snapshots."
},
},
render: (args) => (
<div className="bg-background p-6 text-foreground"><MeterRow {...args} /></div>
),
} satisfies Meta<typeof ContextUsageMeter>;
export default meta;
type Story = StoryObj<typeof meta>;
export const InTask: Story = { render: () => <TaskPage /> };
export const AllStatesGallery: Story = { render: () => <AllStates /> };
export const BreakdownNearCompaction: Story = { render: () => <Breakdown usage={USAGE.nearCompaction} /> };
export const BreakdownWorking: Story = { render: () => <Breakdown usage={USAGE.working} /> };
export const BreakdownClaudeWithCost: Story = { render: () => <Breakdown usage={USAGE.claudeWithCost} /> };