fix(cli): include subagent costs in session total by alex-alecu · Pull Request #9448 · Kilo-Org/kilocode

alex-alecu · 2026-04-24T03:17:31Z

Why

When a session asked the AI to split its work into helper agents, the price shown at the bottom of the screen only counted the main chat and ignored everything the helpers spent. This made the running total look much smaller than it really was.

What changed

Each helper agent now reports its total spending back to the line of the conversation that started it, and the system adds that amount on top of whatever that line already cost. Helpers that launch their own helpers work the same way — each layer rolls up into the one above it — so by the time you look at the main session, the number includes every helper, no matter how deep. Resuming a paused helper only adds what was spent this time around, not a duplicate of the older amount. The price shown in the terminal footer, the sidebar, the web view, and the editor side panel are all updated automatically because they read from the same number.

How to test

Start a new chat and ask the assistant to use a few helper agents to do something (for example: "Use 3 explore subagents in parallel to look at different parts of the codebase").
Wait for all the helpers to finish.
Check the cost shown in the terminal footer and the sidebar — it should now include the helpers' spending, not just the main chat's.
Try a task that uses nested helpers (a helper that spawns another helper) and confirm the total includes every level.

Demo

Bun dev (this fix)

Kilo 7.2.22

When a session spawned subagents via the task tool, the displayed cost reflected only the parent's own LLM steps. Propagate each subagent's total up to the invoking assistant message so every UI sums the full tree.

kilo-code-bot · 2026-04-24T03:23:31Z

Code Review Summary

Status: No Issues Found | Recommendation: Merge

Files Reviewed (8 files)

.changeset/fix-subagent-cost-propagation.md
packages/opencode/src/cli/cmd/stats.ts
packages/opencode/src/kilocode/session/cost-propagation.ts
packages/opencode/src/session/processor.ts
packages/opencode/src/session/prompt.ts
packages/opencode/src/tool/task.ts
packages/opencode/test/kilocode/cost-propagation.test.ts
packages/opencode/test/kilocode/stats-subagent-cost.test.ts

_{Reviewed by gpt-5.4-2026-03-05 · 2,353,038 tokens}

finish-step and cleanup previously re-wrote the parent assistant message with a stale in-memory cost, clobbering the subagent cost written by task.ts during tool execution. Refresh from DB before each write so the propagated cost is preserved across steps. Verified live via side-by-side `kilo serve` vs dev `bun serve` with 2 parallel subagents; parent now shows own LLM + children, matching real spend.

The task tool propagates each child session's total cost into the parent's tool-wrapper assistant message. Counting both root and child sessions in `kilo stats` would double-count that contribution. Filter `getAllSessions()` to root sessions (parent_id IS NULL), matching how the TUI session list and web sidebar already treat child sessions.

alex-alecu · 2026-04-25T07:19:00Z

VS Code

On this branch with the fix - $0.99

On main - $0.54

jrf0110 · 2026-04-25T14:36:42Z

+          const cost = (() => {
+            const parts = message.parts.filter(
+              (part: MessageV2.Part): part is MessageV2.StepFinishPart => part.type === "step-finish",
+            )
+            if (parts.length === 0) return message.info.cost || 0
+            return parts.reduce((sum: number, part: MessageV2.StepFinishPart) => sum + part.cost, 0)
+          })()
+          if (!session.parentID) sessionCost += message.info.cost || 0


Just some code golfing clarity suggestion. Take it or leave it!

There's a lot of unnecessary code here we can make tighter. For instance, the type of message is already known and each message part is already expressed as a discriminated union on part.type, so there's no need to express this type guard here:

(part: MessageV2.Part): part is MessageV2.StepFinishPart => part.type === "step-finish"

You can remove all of the types and it works the same:

(part) => part.type === "step-finish"

And since we're already using .filter and .reduce, we may as well lean into that style and chain them together:

Suggested change

const cost = (() => {

const parts = message.parts.filter(

(part: MessageV2.Part): part is MessageV2.StepFinishPart => part.type === "step-finish",

)

if (parts.length === 0) return message.info.cost || 0

return parts.reduce((sum: number, part: MessageV2.StepFinishPart) => sum + part.cost, 0)

})()

if (!session.parentID) sessionCost += message.info.cost || 0

const cost = message.parts

.filter(part => part.type === "step-finish")

.reduce((sum, part) => sum + part.cost, message.info.cost || 0)

Done in 1eaf409.

alex-alecu · 2026-04-27T08:54:47Z

Blocked before running requested workflow: the worktree was already dirty at startup, so I did not run merge-with-main, fix-review, tests, or any commands that could overwrite user work. Dirty files detected:

.kilo/package-lock.json
.kilocode/package-lock.json
packages/opencode/test/session/prompt-effect.test.ts

Per the safety rules, these pre-existing changes need to be resolved or confirmed before continuing.

Add missing 'variant' property to task tool metadata in prompt-effect test, required after upstream added model variant support to the task tool's ExecuteResult type.

…kilocode into fix/costs-of-subagents

) * Port from Kilo-Org/kilocode#9448: roll up subagent costs into parent session total Child subagents built by delegate_task() each track their own session_estimated_cost_usd, but the parent agent's total never folded those numbers in. On runs where the parent mostly delegates and the children do the expensive work, the footer/UI was reporting a fraction of the actual spend — sometimes $0.00 when the parent itself made no billed calls. Fix: - Capture each child's session_estimated_cost_usd into _child_cost_usd on the result entry (before child.close() drops the counter). - After the existing subagent_stop hook loop, sum the children's costs and add the total to parent.session_estimated_cost_usd. - Promote session_cost_source from 'none' -> 'subagent' when the parent had no direct spend but children did, so the UI doesn't label the total as having unknown provenance. Real sources (openrouter, anthropic, etc.) are preserved. Nested orchestrator -> worker trees roll up naturally: each layer's own delegate_task() folds its direct children in, and when the orchestrator itself returns, its parent folds the orchestrator's now-inflated total on top. Internal fields (_child_cost_usd, _child_role) are stripped from the results dict before it's serialised back to the model — same contract as _child_role already followed. Tests: TestSubagentCostRollup (5 cases) covers single-child, batch, zero-cost-children, preserved-source, and legacy-fixture paths. Source: Kilo-Org/kilocode#9448 * fix(web): scope dashboard config Reset button to the current tab Reported by @ykmfb001 via X: clicking 'Restore Defaults' (恢复默认值) on the Auxiliary page wiped the entire config.yaml to defaults, not just the auxiliary section. The button sits next to the category tabs and users reasonably assumed 'reset this tab', not 'reset everything'. Changes: - handleReset now scopes to the fields in the current view: active category's fields (form mode) or search-matched fields (search mode). Only those keys are copied from defaults; the rest of the config is left alone. - Added a window.confirm() with the scope name before applying. - Button is hidden in YAML mode (scoping doesn't apply there). - Tooltip/aria-label now name the scope, e.g. 'Reset Auxiliary to defaults'. - i18n: new resetScopeTooltip / confirmResetScope / resetScopeToast strings in en + zh; resetDefaults key preserved for compat.

…813) * Port from Kilo-Org/kilocode#9448: roll up subagent costs into parent session total Child subagents built by delegate_task() each track their own session_estimated_cost_usd, but the parent agent's total never folded those numbers in. On runs where the parent mostly delegates and the children do the expensive work, the footer/UI was reporting a fraction of the actual spend — sometimes $0.00 when the parent itself made no billed calls. Fix: - Capture each child's session_estimated_cost_usd into _child_cost_usd on the result entry (before child.close() drops the counter). - After the existing subagent_stop hook loop, sum the children's costs and add the total to parent.session_estimated_cost_usd. - Promote session_cost_source from 'none' -> 'subagent' when the parent had no direct spend but children did, so the UI doesn't label the total as having unknown provenance. Real sources (openrouter, anthropic, etc.) are preserved. Nested orchestrator -> worker trees roll up naturally: each layer's own delegate_task() folds its direct children in, and when the orchestrator itself returns, its parent folds the orchestrator's now-inflated total on top. Internal fields (_child_cost_usd, _child_role) are stripped from the results dict before it's serialised back to the model — same contract as _child_role already followed. Tests: TestSubagentCostRollup (5 cases) covers single-child, batch, zero-cost-children, preserved-source, and legacy-fixture paths. Source: Kilo-Org/kilocode#9448 * fix(web): scope dashboard config Reset button to the current tab Reported by @ykmfb001 via X: clicking 'Restore Defaults' (恢复默认值) on the Auxiliary page wiped the entire config.yaml to defaults, not just the auxiliary section. The button sits next to the category tabs and users reasonably assumed 'reset this tab', not 'reset everything'. Changes: - handleReset now scopes to the fields in the current view: active category's fields (form mode) or search-matched fields (search mode). Only those keys are copied from defaults; the rest of the config is left alone. - Added a window.confirm() with the scope name before applying. - Button is hidden in YAML mode (scoping doesn't apply there). - Tooltip/aria-label now name the scope, e.g. 'Reset Auxiliary to defaults'. - i18n: new resetScopeTooltip / confirmResetScope / resetScopeToast strings in en + zh; resetDefaults key preserved for compat.

…e progress Three feedback items rolled into one focused change: 1. Cost tracking — the per-child cost rollup at the end of delegate_task() already existed (Kilo-Org/kilocode#9448 port) but the user couldn't see anything about subagent spend until the parent's session footer at end of turn. Now we emit visible status: - Every 30s during a child run (heartbeat-piggyback): model · tool · iteration · elapsed · running tokens · running cost. - On each child completion: status icon · model · duration · tokens · cost. - On full delegate_task() return: N/M subagents ok · total duration · batch child cost · session running total. All routed through _emit_status() so the lines reach both CLI scrollback and TUI/gateway status channels (per the lifecycle visibility convention in the hermes-agent-internals skill). 2. Per-call model selection — added 'model' to the delegate_task tool schema at both the top level and inside tasks[]. Precedence: per-task → top-level → delegation.model config → parent's model. Lets the orchestrator right-size each child (Haiku for retrieval/grep, Sonnet for analysis, Opus for deep reasoning) without editing config.yaml. Plumbed through to _build_child_agent's existing 'model' kwarg — the credential resolution path already supports per-child models, this just exposes the knob. 3. Progress visibility — until now, a long delegate_task showed only the parent's spinner_text "🔀 delegate ... 506.2s" with no signal about what the subagent was doing. The heartbeat thread already polled child.get_activity_summary() for the GATEWAY's _touch_activity (so inactivity timeout doesn't fire), but it was invisible to the user. Now the same poll cycle also routes a human-readable line through _emit_status. Same pattern as the streaming-stall heartbeat fix (commit 03890b6c) — piggyback existing thread, no new cadence. Tests: tests/tools/test_delegate.py 121/121 pass. User-visible diff (during a 3-child delegate run): ┊ 🔀 [0] claude-haiku-4-5 · salesforce_fetch_case (iter 2/30) · 30s elapsed | 4,210↓/127↑ tok | $0.0008 ┊ 🔀 [1] claude-sonnet-4-6 · search_files (iter 5/30) · 60s elapsed | 18,332↓/892↑ tok | $0.0772 ┊ ✅ subagent [0] claude-haiku-4-5 · completed in 47.2s | 9,217↓/411↑ tok | $0.0019 ┊ ✅ subagent [1] claude-sonnet-4-6 · completed in 142.8s | 38,201↓/2,103↑ tok | $0.1462 ┊ 🔀 delegate done · 3 subagents ok · 603.2s · children=$0.4287 · session=$0.7912 Replaces the prior 1-line "🔀 delegate ... 506.2s" with no cost insight.

…sResearch#16813) * Port from Kilo-Org/kilocode#9448: roll up subagent costs into parent session total Child subagents built by delegate_task() each track their own session_estimated_cost_usd, but the parent agent's total never folded those numbers in. On runs where the parent mostly delegates and the children do the expensive work, the footer/UI was reporting a fraction of the actual spend — sometimes $0.00 when the parent itself made no billed calls. Fix: - Capture each child's session_estimated_cost_usd into _child_cost_usd on the result entry (before child.close() drops the counter). - After the existing subagent_stop hook loop, sum the children's costs and add the total to parent.session_estimated_cost_usd. - Promote session_cost_source from 'none' -> 'subagent' when the parent had no direct spend but children did, so the UI doesn't label the total as having unknown provenance. Real sources (openrouter, anthropic, etc.) are preserved. Nested orchestrator -> worker trees roll up naturally: each layer's own delegate_task() folds its direct children in, and when the orchestrator itself returns, its parent folds the orchestrator's now-inflated total on top. Internal fields (_child_cost_usd, _child_role) are stripped from the results dict before it's serialised back to the model — same contract as _child_role already followed. Tests: TestSubagentCostRollup (5 cases) covers single-child, batch, zero-cost-children, preserved-source, and legacy-fixture paths. Source: Kilo-Org/kilocode#9448 * fix(web): scope dashboard config Reset button to the current tab Reported by @ykmfb001 via X: clicking 'Restore Defaults' (恢复默认值) on the Auxiliary page wiped the entire config.yaml to defaults, not just the auxiliary section. The button sits next to the category tabs and users reasonably assumed 'reset this tab', not 'reset everything'. Changes: - handleReset now scopes to the fields in the current view: active category's fields (form mode) or search-matched fields (search mode). Only those keys are copied from defaults; the rest of the config is left alone. - Added a window.confirm() with the scope name before applying. - Button is hidden in YAML mode (scoping doesn't apply there). - Tooltip/aria-label now name the scope, e.g. 'Reset Auxiliary to defaults'. - i18n: new resetScopeTooltip / confirmResetScope / resetScopeToast strings in en + zh; resetDefaults key preserved for compat.

fix(cli): include subagent costs in session total

…sResearch#16813) * Port from Kilo-Org/kilocode#9448: roll up subagent costs into parent session total Child subagents built by delegate_task() each track their own session_estimated_cost_usd, but the parent agent's total never folded those numbers in. On runs where the parent mostly delegates and the children do the expensive work, the footer/UI was reporting a fraction of the actual spend — sometimes $0.00 when the parent itself made no billed calls. Fix: - Capture each child's session_estimated_cost_usd into _child_cost_usd on the result entry (before child.close() drops the counter). - After the existing subagent_stop hook loop, sum the children's costs and add the total to parent.session_estimated_cost_usd. - Promote session_cost_source from 'none' -> 'subagent' when the parent had no direct spend but children did, so the UI doesn't label the total as having unknown provenance. Real sources (openrouter, anthropic, etc.) are preserved. Nested orchestrator -> worker trees roll up naturally: each layer's own delegate_task() folds its direct children in, and when the orchestrator itself returns, its parent folds the orchestrator's now-inflated total on top. Internal fields (_child_cost_usd, _child_role) are stripped from the results dict before it's serialised back to the model — same contract as _child_role already followed. Tests: TestSubagentCostRollup (5 cases) covers single-child, batch, zero-cost-children, preserved-source, and legacy-fixture paths. Source: Kilo-Org/kilocode#9448 * fix(web): scope dashboard config Reset button to the current tab Reported by @ykmfb001 via X: clicking 'Restore Defaults' (恢复默认值) on the Auxiliary page wiped the entire config.yaml to defaults, not just the auxiliary section. The button sits next to the category tabs and users reasonably assumed 'reset this tab', not 'reset everything'. Changes: - handleReset now scopes to the fields in the current view: active category's fields (form mode) or search-matched fields (search mode). Only those keys are copied from defaults; the rest of the config is left alone. - Added a window.confirm() with the scope name before applying. - Button is hidden in YAML mode (scoping doesn't apply there). - Tooltip/aria-label now name the scope, e.g. 'Reset Auxiliary to defaults'. - i18n: new resetScopeTooltip / confirmResetScope / resetScopeToast strings in en + zh; resetDefaults key preserved for compat.

…813) * Port from Kilo-Org/kilocode#9448: roll up subagent costs into parent session total Child subagents built by delegate_task() each track their own session_estimated_cost_usd, but the parent agent's total never folded those numbers in. On runs where the parent mostly delegates and the children do the expensive work, the footer/UI was reporting a fraction of the actual spend — sometimes $0.00 when the parent itself made no billed calls. Fix: - Capture each child's session_estimated_cost_usd into _child_cost_usd on the result entry (before child.close() drops the counter). - After the existing subagent_stop hook loop, sum the children's costs and add the total to parent.session_estimated_cost_usd. - Promote session_cost_source from 'none' -> 'subagent' when the parent had no direct spend but children did, so the UI doesn't label the total as having unknown provenance. Real sources (openrouter, anthropic, etc.) are preserved. Nested orchestrator -> worker trees roll up naturally: each layer's own delegate_task() folds its direct children in, and when the orchestrator itself returns, its parent folds the orchestrator's now-inflated total on top. Internal fields (_child_cost_usd, _child_role) are stripped from the results dict before it's serialised back to the model — same contract as _child_role already followed. Tests: TestSubagentCostRollup (5 cases) covers single-child, batch, zero-cost-children, preserved-source, and legacy-fixture paths. Source: Kilo-Org/kilocode#9448 * fix(web): scope dashboard config Reset button to the current tab Reported by @ykmfb001 via X: clicking 'Restore Defaults' (恢复默认值) on the Auxiliary page wiped the entire config.yaml to defaults, not just the auxiliary section. The button sits next to the category tabs and users reasonably assumed 'reset this tab', not 'reset everything'. Changes: - handleReset now scopes to the fields in the current view: active category's fields (form mode) or search-matched fields (search mode). Only those keys are copied from defaults; the rest of the config is left alone. - Added a window.confirm() with the scope name before applying. - Button is hidden in YAML mode (scoping doesn't apply there). - Tooltip/aria-label now name the scope, e.g. 'Reset Auxiliary to defaults'. - i18n: new resetScopeTooltip / confirmResetScope / resetScopeToast strings in en + zh; resetDefaults key preserved for compat.

…sResearch#16813) * Port from Kilo-Org/kilocode#9448: roll up subagent costs into parent session total Child subagents built by delegate_task() each track their own session_estimated_cost_usd, but the parent agent's total never folded those numbers in. On runs where the parent mostly delegates and the children do the expensive work, the footer/UI was reporting a fraction of the actual spend — sometimes $0.00 when the parent itself made no billed calls. Fix: - Capture each child's session_estimated_cost_usd into _child_cost_usd on the result entry (before child.close() drops the counter). - After the existing subagent_stop hook loop, sum the children's costs and add the total to parent.session_estimated_cost_usd. - Promote session_cost_source from 'none' -> 'subagent' when the parent had no direct spend but children did, so the UI doesn't label the total as having unknown provenance. Real sources (openrouter, anthropic, etc.) are preserved. Nested orchestrator -> worker trees roll up naturally: each layer's own delegate_task() folds its direct children in, and when the orchestrator itself returns, its parent folds the orchestrator's now-inflated total on top. Internal fields (_child_cost_usd, _child_role) are stripped from the results dict before it's serialised back to the model — same contract as _child_role already followed. Tests: TestSubagentCostRollup (5 cases) covers single-child, batch, zero-cost-children, preserved-source, and legacy-fixture paths. Source: Kilo-Org/kilocode#9448 * fix(web): scope dashboard config Reset button to the current tab Reported by @ykmfb001 via X: clicking 'Restore Defaults' (恢复默认值) on the Auxiliary page wiped the entire config.yaml to defaults, not just the auxiliary section. The button sits next to the category tabs and users reasonably assumed 'reset this tab', not 'reset everything'. Changes: - handleReset now scopes to the fields in the current view: active category's fields (form mode) or search-matched fields (search mode). Only those keys are copied from defaults; the rest of the config is left alone. - Added a window.confirm() with the scope name before applying. - Button is hidden in YAML mode (scoping doesn't apply there). - Tooltip/aria-label now name the scope, e.g. 'Reset Auxiliary to defaults'. - i18n: new resetScopeTooltip / confirmResetScope / resetScopeToast strings in en + zh; resetDefaults key preserved for compat.

…session total Child subagents built by delegate_task() each track their own session_estimated_cost_usd, but the parent agent's total never folded those numbers in. On runs where the parent mostly delegates and the children do the expensive work, the footer/UI was reporting a fraction of the actual spend — sometimes $0.00 when the parent itself made no billed calls. Fix: - Capture each child's session_estimated_cost_usd into _child_cost_usd on the result entry (before child.close() drops the counter). - After the existing subagent_stop hook loop, sum the children's costs and add the total to parent.session_estimated_cost_usd. - Promote session_cost_source from 'none' -> 'subagent' when the parent had no direct spend but children did, so the UI doesn't label the total as having unknown provenance. Real sources (openrouter, anthropic, etc.) are preserved. Nested orchestrator -> worker trees roll up naturally: each layer's own delegate_task() folds its direct children in, and when the orchestrator itself returns, its parent folds the orchestrator's now-inflated total on top. Internal fields (_child_cost_usd, _child_role) are stripped from the results dict before it's serialised back to the model — same contract as _child_role already followed. Tests: TestSubagentCostRollup (5 cases) covers single-child, batch, zero-cost-children, preserved-source, and legacy-fixture paths. Source: Kilo-Org/kilocode#9448

fix(cli): include subagent costs in session total

fix(cli): include subagent costs in session total (#6321)

73ab363

When a session spawned subagents via the task tool, the displayed cost reflected only the parent's own LLM steps. Propagate each subagent's total up to the invoking assistant message so every UI sums the full tree.

kilo-code-bot Bot reviewed Apr 24, 2026

View reviewed changes

Comment thread packages/opencode/src/tool/task.ts

alex-alecu added 2 commits April 24, 2026 07:26

fix(cli): serialize concurrent subagent cost propagation

ae0c437

kilo-code-bot Bot reviewed Apr 24, 2026

View reviewed changes

Comment thread packages/opencode/src/session/processor.ts Outdated

kilo-code-bot Bot reviewed Apr 24, 2026

View reviewed changes

Comment thread packages/opencode/src/cli/cmd/stats.ts Outdated

alex-alecu added 3 commits April 24, 2026 19:19

fix(cli): ignore deleted cost sync

1230a3a

fix(cli): count subagent stats

bc90a50

chore(cli): mark stats cost line

7a9da3f

jrf0110 reviewed Apr 25, 2026

View reviewed changes

jrf0110 approved these changes Apr 25, 2026

View reviewed changes

alex-alecu added 2 commits April 27, 2026 10:21

refactor(cli): simplify stats cost

1eaf409

Merge branch 'main' into fix/costs-of-subagents

87ba16c

alex-alecu added 3 commits April 27, 2026 13:03

Merge remote-tracking branch 'origin/main' into fix/costs-of-subagents

67993d0

chore(cli): fix type error after main merge

16abe96

Add missing 'variant' property to task tool metadata in prompt-effect test, required after upstream added model variant support to the task tool's ExecuteResult type.

Merge branch 'fix/costs-of-subagents' of https://github.com/Kilo-Org/…

e101781

…kilocode into fix/costs-of-subagents

alex-alecu merged commit 5be897c into main Apr 27, 2026
15 checks passed

alex-alecu deleted the fix/costs-of-subagents branch April 27, 2026 10:30

teknium1 mentioned this pull request Apr 28, 2026

Port Kilo#9448: roll up subagent costs into parent session total NousResearch/hermes-agent#16741

Closed

github-actions Bot mentioned this pull request Apr 28, 2026

🦞 OpenClaw Ecosystem Digest 2026-04-28 duanyytop/agents-radar#819

Closed

jliounis pushed a commit to jliounis/kilocode that referenced this pull request May 18, 2026

Merge pull request Kilo-Org#9448 from Kilo-Org/fix/costs-of-subagents

943be4a

fix(cli): include subagent costs in session total

mjwicker mentioned this pull request May 25, 2026

bug: delegate_task subagent costs never persisted to state DB — in-memory only NousResearch/hermes-agent#32220

Open

t7tran pushed a commit to t7tran/kilocode that referenced this pull request Aug 14, 2026

Merge pull request Kilo-Org#9448 from Kilo-Org/fix/costs-of-subagents

2dcee29

fix(cli): include subagent costs in session total

Navigation Menu

Uh oh!

fix(cli): include subagent costs in session total - #9448

fix(cli): include subagent costs in session total#9448
alex-alecu merged 12 commits into
mainfrom
fix/costs-of-subagents

alex-alecu commented Apr 24, 2026 •

edited

Loading

Uh oh!

Uh oh!

kilo-code-bot Bot commented Apr 24, 2026 •

edited

Loading

Uh oh!

Uh oh!

Uh oh!

alex-alecu commented Apr 25, 2026

Uh oh!

jrf0110 Apr 25, 2026

Uh oh!

alex-alecu Apr 27, 2026

Uh oh!

alex-alecu commented Apr 27, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

alex-alecu commented Apr 24, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Why

What changed

How to test

Demo

Bun dev (this fix)

Kilo 7.2.22

Uh oh!

Uh oh!

kilo-code-bot Bot commented Apr 24, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Code Review Summary

Uh oh!

Uh oh!

Uh oh!

alex-alecu commented Apr 25, 2026

VS Code

On this branch with the fix - $0.99

On main - $0.54

Uh oh!

jrf0110 Apr 25, 2026

Choose a reason for hiding this comment

Uh oh!

alex-alecu Apr 27, 2026

Choose a reason for hiding this comment

Uh oh!

alex-alecu commented Apr 27, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

alex-alecu commented Apr 24, 2026 •

edited

Loading

kilo-code-bot Bot commented Apr 24, 2026 •

edited

Loading