composer-2.5
Running composer-2.5 inside cursor.
Workflow
FastAPI: Add POST /api/v1/projects/{project_id}/tasks endpoint Plan → Review plan → Execute → Review & fix → Open PR → Verify PR → Verify e2e
Every run uses the same steps in the same order. Full workflow definition →
All steps run as one workflow, inside a single Docker container.
Swipe to view more
| # | Step | Kind | What happens |
|---|---|---|---|
| 1 | pullIssue | host | Fetches the GitHub issue and creates a branch |
| 2 | plan | agent | Drafts a plan from the ticket, including tests |
| 3 | reviewPlan | agent | Always runs; returns the full final plan |
| 4 | execute | agent | Implements code and tests from the reviewed plan |
| 5 | reviewAndCorrect | agent | Runs checks, reviews against the plan, fixes, re-runs checks |
| 6 | openPullRequest | agent | Commits, pushes, opens a pull request into main |
| 7 | verifyPullRequest | host | Checks that the exact pull request is open |
| 8 | verifyPullRequestCheck | host | Waits for the required end-to-end check to pass |
| 9 | summarizeUsage | host | Totals tokens and cost |
| 10 | score | host | Records the final result |
Runs
Speed
Reasoning
Run 5 $0.33 PASS
Steps
Swipe to view more
| Step | Status | Cost | Time | In tok | Out tok | Tools |
|---|---|---|---|---|---|---|
| pullIssue | succeeded | $0.00 | — | 0 | 0 | 0 |
| plan | succeeded | $0.06 | 2m 57s | 25,769 | 5,263 | 23 |
| reviewPlan | succeeded | $0.05 | 0m 55s | 21,338 | 5,470 | 23 |
| execute | succeeded | $0.07 | 0m 54s | 21,047 | 4,203 | 31 |
| reviewAndCorrect | succeeded | $0.09 | 1m 26s | 25,040 | 6,329 | 38 |
| openPullRequest | succeeded | $0.06 | 0m 46s | 16,853 | 1,696 | 18 |
| verifyPullRequest | succeeded | $0.00 | 0m 01s | 0 | 0 | 0 |
| verifyPullRequestCheck | succeeded | $0.00 | 0m 32s | 0 | 0 | 0 |
| summarizeUsage | succeeded | $0.00 | — | 0 | 0 | 0 |
| score | succeeded | $0.00 | — | 0 | 0 | 0 |
Run totals
- Cost
- $0.33
- Input tokens
- 110,047
- Output tokens
- 22,961
- Cache-read tokens
- 1,082,016
- Tool calls
- 133
Tool call mix
- read
- 72
- shell
- 30
- edit
- 8
- glob
- 8
- grep
- 8
- task
- 3
- createPlan
- 2
- readLints
- 2
Run 4 $0.31 PASS
Steps
Swipe to view more
| Step | Status | Cost | Time | In tok | Out tok | Tools |
|---|---|---|---|---|---|---|
| pullIssue | succeeded | $0.00 | — | 0 | 0 | 0 |
| plan | succeeded | $0.05 | 2m 34s | 29,582 | 5,223 | 21 |
| reviewPlan | succeeded | $0.05 | 0m 55s | 21,796 | 4,377 | 23 |
| execute | succeeded | $0.07 | 2m 44s | 19,602 | 3,767 | 29 |
| reviewAndCorrect | succeeded | $0.08 | 1m 32s | 27,669 | 6,060 | 32 |
| openPullRequest | succeeded | $0.06 | 0m 45s | 18,299 | 2,077 | 19 |
| verifyPullRequest | succeeded | $0.00 | 0m 01s | 0 | 0 | 0 |
| verifyPullRequestCheck | succeeded | $0.00 | 0m 22s | 0 | 0 | 0 |
| summarizeUsage | succeeded | $0.00 | — | 0 | 0 | 0 |
| score | succeeded | $0.00 | — | 0 | 0 | 0 |
Run totals
- Cost
- $0.31
- Input tokens
- 116,948
- Output tokens
- 21,504
- Cache-read tokens
- 998,233
- Tool calls
- 124
Tool call mix
- read
- 69
- shell
- 29
- glob
- 8
- edit
- 7
- grep
- 7
- createPlan
- 2
- task
- 2
Run 3 $0.31 PASS
Steps
Swipe to view more
| Step | Status | Cost | Time | In tok | Out tok | Tools |
|---|---|---|---|---|---|---|
| pullIssue | succeeded | $0.00 | — | 0 | 0 | 0 |
| plan | succeeded | $0.05 | 3m 03s | 26,317 | 6,336 | 22 |
| reviewPlan | succeeded | $0.04 | 1m 38s | 20,840 | 4,566 | 22 |
| execute | succeeded | $0.05 | 1m 13s | 21,480 | 3,658 | 27 |
| reviewAndCorrect | succeeded | $0.08 | 1m 29s | 26,253 | 3,730 | 30 |
| openPullRequest | succeeded | $0.08 | 1m 03s | 18,491 | 2,037 | 23 |
| verifyPullRequest | succeeded | $0.00 | 0m 01s | 0 | 0 | 0 |
| verifyPullRequestCheck | succeeded | $0.00 | 0m 22s | 0 | 0 | 0 |
| summarizeUsage | succeeded | $0.00 | — | 0 | 0 | 0 |
| score | succeeded | $0.00 | — | 0 | 0 | 0 |
Run totals
- Cost
- $0.31
- Input tokens
- 113,381
- Output tokens
- 20,327
- Cache-read tokens
- 993,322
- Tool calls
- 124
Tool call mix
- read
- 68
- shell
- 34
- edit
- 8
- glob
- 6
- grep
- 4
- createPlan
- 2
- task
- 2
Run 2 $0.28 PASS
Steps
Swipe to view more
| Step | Status | Cost | Time | In tok | Out tok | Tools |
|---|---|---|---|---|---|---|
| pullIssue | succeeded | $0.00 | — | 0 | 0 | 0 |
| plan | succeeded | $0.05 | 2m 40s | 26,363 | 5,874 | 24 |
| reviewPlan | succeeded | $0.05 | 1m 17s | 21,379 | 4,897 | 24 |
| execute | succeeded | $0.05 | 1m 14s | 21,089 | 3,733 | 27 |
| reviewAndCorrect | succeeded | $0.06 | 0m 59s | 24,022 | 2,118 | 25 |
| openPullRequest | succeeded | $0.07 | 0m 51s | 18,625 | 1,978 | 23 |
| verifyPullRequest | succeeded | $0.00 | 0m 01s | 0 | 0 | 0 |
| verifyPullRequestCheck | succeeded | $0.00 | 0m 21s | 0 | 0 | 0 |
| summarizeUsage | succeeded | $0.00 | — | 0 | 0 | 0 |
| score | succeeded | $0.00 | — | 0 | 0 | 0 |
Run totals
- Cost
- $0.28
- Input tokens
- 111,478
- Output tokens
- 18,600
- Cache-read tokens
- 891,828
- Tool calls
- 123
Tool call mix
- read
- 66
- shell
- 33
- edit
- 8
- glob
- 6
- grep
- 5
- createPlan
- 2
- task
- 2
- readLints
- 1
Run 1 $0.28 PASS
Steps
Swipe to view more
| Step | Status | Cost | Time | In tok | Out tok | Tools |
|---|---|---|---|---|---|---|
| pullIssue | succeeded | $0.00 | — | 0 | 0 | 0 |
| plan | succeeded | $0.05 | 1m 09s | 20,190 | 5,224 | 25 |
| reviewPlan | succeeded | $0.05 | 0m 44s | 21,564 | 5,122 | 26 |
| execute | succeeded | $0.05 | 3m 16s | 21,369 | 4,199 | 26 |
| reviewAndCorrect | succeeded | $0.06 | 0m 39s | 26,075 | 1,630 | 23 |
| openPullRequest | succeeded | $0.07 | 0m 48s | 19,257 | 1,984 | 22 |
| verifyPullRequest | succeeded | $0.00 | 0m 01s | 0 | 0 | 0 |
| verifyPullRequestCheck | succeeded | $0.00 | — | 0 | 0 | 0 |
| summarizeUsage | succeeded | $0.00 | — | 0 | 0 | 0 |
| score | succeeded | $0.00 | — | 0 | 0 | 0 |
Run totals
- Cost
- $0.28
- Input tokens
- 108,455
- Output tokens
- 18,159
- Cache-read tokens
- 918,294
- Tool calls
- 122
Tool call mix
- read
- 67
- shell
- 31
- edit
- 9
- glob
- 7
- grep
- 6
- createPlan
- 2
No runs match these filters.