task stringclasses 207
values | source_trajectory_id stringclasses 41
values | source_trajectory_sha256 stringclasses 207
values | lang stringclasses 16
values | category stringclasses 141
values | domain stringclasses 2
values | verifier stringclasses 2
values | split stringclasses 2
values | teacher_runtime stringclasses 2
values | teacher_model stringclasses 1
value | reasoning_effort stringclasses 4
values | provider stringclasses 3
values | observed_models listlengths 1 1 | model_attested bool 1
class | trace_format stringclasses 1
value | tools_used listlengths 1 6 | derivation stringclasses 1
value | assistant_step int64 1 29 | assistant_steps int64 5 29 | target_message_index int64 1 58 | original_n_messages int64 6 13 ⌀ | n_messages int64 2 59 | messages listlengths 2 59 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
bash-it-journalwindow | bash-it-journalwindow:c880e6f02ec4083a27b6 | c880e6f02ec4083a27b6ae87dc1d398c4b1160fb39bcc4569321910696372ad1 | bash | integration-operations | agent | acceptance-tests+protected-file-hash+independent-review | val | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"edit",
"read"
] | cumulative-next-assistant-v1 | 8 | 12 | 8 | 13 | 9 | [
{
"role": "user",
"content": "The journalwindow helper already builds deterministic journalctl queries for unit, severity, boot, and time filters; preserves multiline messages; redacts configured literal tokens; and prints a shell-exact reproduction command. Its clock-order check, however, misses a backward... |
bash-it-journalwindow | bash-it-journalwindow:c880e6f02ec4083a27b6 | c880e6f02ec4083a27b6ae87dc1d398c4b1160fb39bcc4569321910696372ad1 | bash | integration-operations | agent | acceptance-tests+protected-file-hash+independent-review | val | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"edit",
"read"
] | cumulative-next-assistant-v1 | 9 | 12 | 9 | 13 | 10 | [
{
"role": "user",
"content": "The journalwindow helper already builds deterministic journalctl queries for unit, severity, boot, and time filters; preserves multiline messages; redacts configured literal tokens; and prints a shell-exact reproduction command. Its clock-order check, however, misses a backward... |
bash-it-journalwindow | bash-it-journalwindow:c880e6f02ec4083a27b6 | c880e6f02ec4083a27b6ae87dc1d398c4b1160fb39bcc4569321910696372ad1 | bash | integration-operations | agent | acceptance-tests+protected-file-hash+independent-review | val | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"edit",
"read"
] | cumulative-next-assistant-v1 | 10 | 12 | 10 | 13 | 11 | [
{
"role": "user",
"content": "The journalwindow helper already builds deterministic journalctl queries for unit, severity, boot, and time filters; preserves multiline messages; redacts configured literal tokens; and prints a shell-exact reproduction command. Its clock-order check, however, misses a backward... |
bash-it-journalwindow | bash-it-journalwindow:c880e6f02ec4083a27b6 | c880e6f02ec4083a27b6ae87dc1d398c4b1160fb39bcc4569321910696372ad1 | bash | integration-operations | agent | acceptance-tests+protected-file-hash+independent-review | val | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"edit",
"read"
] | cumulative-next-assistant-v1 | 11 | 12 | 11 | 13 | 12 | [
{
"role": "user",
"content": "The journalwindow helper already builds deterministic journalctl queries for unit, severity, boot, and time filters; preserves multiline messages; redacts configured literal tokens; and prints a shell-exact reproduction command. Its clock-order check, however, misses a backward... |
bash-it-journalwindow | bash-it-journalwindow:c880e6f02ec4083a27b6 | c880e6f02ec4083a27b6ae87dc1d398c4b1160fb39bcc4569321910696372ad1 | bash | integration-operations | agent | acceptance-tests+protected-file-hash+independent-review | val | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"edit",
"read"
] | cumulative-next-assistant-v1 | 12 | 12 | 12 | 13 | 13 | [
{
"role": "user",
"content": "The journalwindow helper already builds deterministic journalctl queries for unit, severity, boot, and time filters; preserves multiline messages; redacts configured literal tokens; and prints a shell-exact reproduction command. Its clock-order check, however, misses a backward... |
behavior-dependency-planning-0166 | behavior-dependency-planning-0166:356afa10c1d021af22a9 | 356afa10c1d021af22a90522f428fbe7aed76f5b87ade3e8254e0f65c371f39f | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 1 | 6 | 1 | 7 | 2 | [
{
"role": "user",
"content": "Reconcile two order records in this sandbox through the genuine local `./commercectl` executable, using Pi's Bash tool. Begin with `./commercectl --help` to learn its interface. Treat that executable as the sole interface to order records: do not inspect or edit the executable,... |
behavior-dependency-planning-0166 | behavior-dependency-planning-0166:356afa10c1d021af22a9 | 356afa10c1d021af22a90522f428fbe7aed76f5b87ade3e8254e0f65c371f39f | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 2 | 6 | 2 | 7 | 3 | [
{
"role": "user",
"content": "Reconcile two order records in this sandbox through the genuine local `./commercectl` executable, using Pi's Bash tool. Begin with `./commercectl --help` to learn its interface. Treat that executable as the sole interface to order records: do not inspect or edit the executable,... |
behavior-dependency-planning-0166 | behavior-dependency-planning-0166:356afa10c1d021af22a9 | 356afa10c1d021af22a90522f428fbe7aed76f5b87ade3e8254e0f65c371f39f | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 3 | 6 | 3 | 7 | 4 | [
{
"role": "user",
"content": "Reconcile two order records in this sandbox through the genuine local `./commercectl` executable, using Pi's Bash tool. Begin with `./commercectl --help` to learn its interface. Treat that executable as the sole interface to order records: do not inspect or edit the executable,... |
behavior-dependency-planning-0166 | behavior-dependency-planning-0166:356afa10c1d021af22a9 | 356afa10c1d021af22a90522f428fbe7aed76f5b87ade3e8254e0f65c371f39f | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 4 | 6 | 4 | 7 | 5 | [
{
"role": "user",
"content": "Reconcile two order records in this sandbox through the genuine local `./commercectl` executable, using Pi's Bash tool. Begin with `./commercectl --help` to learn its interface. Treat that executable as the sole interface to order records: do not inspect or edit the executable,... |
behavior-dependency-planning-0166 | behavior-dependency-planning-0166:356afa10c1d021af22a9 | 356afa10c1d021af22a90522f428fbe7aed76f5b87ade3e8254e0f65c371f39f | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 5 | 6 | 5 | 7 | 6 | [
{
"role": "user",
"content": "Reconcile two order records in this sandbox through the genuine local `./commercectl` executable, using Pi's Bash tool. Begin with `./commercectl --help` to learn its interface. Treat that executable as the sole interface to order records: do not inspect or edit the executable,... |
behavior-dependency-planning-0166 | behavior-dependency-planning-0166:356afa10c1d021af22a9 | 356afa10c1d021af22a90522f428fbe7aed76f5b87ade3e8254e0f65c371f39f | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 6 | 6 | 6 | 7 | 7 | [
{
"role": "user",
"content": "Reconcile two order records in this sandbox through the genuine local `./commercectl` executable, using Pi's Bash tool. Begin with `./commercectl --help` to learn its interface. Treat that executable as the sole interface to order records: do not inspect or edit the executable,... |
behavior-dependency-planning-0018 | behavior-dependency-planning-0018:6eb9077df5cdcd08c520 | 6eb9077df5cdcd08c520e9e6e62d83d444b0495ec12d0bd3b9fe4505d5d787ef | python | behavior | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | medium | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 1 | 5 | 1 | 6 | 2 | [
{
"role": "user",
"content": "Work inside the supplied sandbox. Read SUBSCRIPTIONS.md before invoking the subscription client. Prepare account-review.md for the service desk by resolving the subscription named “Family Fiber Subscription” at “Residence Account” and the subscription named “Studio Tablet Subsc... |
behavior-dependency-planning-0018 | behavior-dependency-planning-0018:6eb9077df5cdcd08c520 | 6eb9077df5cdcd08c520e9e6e62d83d444b0495ec12d0bd3b9fe4505d5d787ef | python | behavior | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | medium | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 2 | 5 | 2 | 6 | 3 | [
{
"role": "user",
"content": "Work inside the supplied sandbox. Read SUBSCRIPTIONS.md before invoking the subscription client. Prepare account-review.md for the service desk by resolving the subscription named “Family Fiber Subscription” at “Residence Account” and the subscription named “Studio Tablet Subsc... |
behavior-dependency-planning-0018 | behavior-dependency-planning-0018:6eb9077df5cdcd08c520 | 6eb9077df5cdcd08c520e9e6e62d83d444b0495ec12d0bd3b9fe4505d5d787ef | python | behavior | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | medium | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 3 | 5 | 3 | 6 | 4 | [
{
"role": "user",
"content": "Work inside the supplied sandbox. Read SUBSCRIPTIONS.md before invoking the subscription client. Prepare account-review.md for the service desk by resolving the subscription named “Family Fiber Subscription” at “Residence Account” and the subscription named “Studio Tablet Subsc... |
behavior-dependency-planning-0018 | behavior-dependency-planning-0018:6eb9077df5cdcd08c520 | 6eb9077df5cdcd08c520e9e6e62d83d444b0495ec12d0bd3b9fe4505d5d787ef | python | behavior | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | medium | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 4 | 5 | 4 | 6 | 5 | [
{
"role": "user",
"content": "Work inside the supplied sandbox. Read SUBSCRIPTIONS.md before invoking the subscription client. Prepare account-review.md for the service desk by resolving the subscription named “Family Fiber Subscription” at “Residence Account” and the subscription named “Studio Tablet Subsc... |
behavior-dependency-planning-0018 | behavior-dependency-planning-0018:6eb9077df5cdcd08c520 | 6eb9077df5cdcd08c520e9e6e62d83d444b0495ec12d0bd3b9fe4505d5d787ef | python | behavior | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | medium | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 5 | 5 | 5 | 6 | 6 | [
{
"role": "user",
"content": "Work inside the supplied sandbox. Read SUBSCRIPTIONS.md before invoking the subscription client. Prepare account-review.md for the service desk by resolving the subscription named “Family Fiber Subscription” at “Residence Account” and the subscription named “Studio Tablet Subsc... |
behavior-dependency-planning-0046 | behavior-dependency-planning-0046:40f0f5e9c1c2f0b3f346 | 40f0f5e9c1c2f0b3f34668557fabea3d49aa5c7202715d04e2a99d3b905b0631 | python | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 1 | 8 | 1 | 9 | 2 | [
{
"role": "user",
"content": "Procurement is reconciling two orders before the morning fulfillment review. Use the genuine local `./orderdesk` executable for every order-system lookup; do not read `orders.db` or its audit log directly. Its built-in `--help` describes the available operations. Find the order... |
behavior-dependency-planning-0046 | behavior-dependency-planning-0046:40f0f5e9c1c2f0b3f346 | 40f0f5e9c1c2f0b3f34668557fabea3d49aa5c7202715d04e2a99d3b905b0631 | python | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 2 | 8 | 2 | 9 | 3 | [
{
"role": "user",
"content": "Procurement is reconciling two orders before the morning fulfillment review. Use the genuine local `./orderdesk` executable for every order-system lookup; do not read `orders.db` or its audit log directly. Its built-in `--help` describes the available operations. Find the order... |
behavior-dependency-planning-0046 | behavior-dependency-planning-0046:40f0f5e9c1c2f0b3f346 | 40f0f5e9c1c2f0b3f34668557fabea3d49aa5c7202715d04e2a99d3b905b0631 | python | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 3 | 8 | 3 | 9 | 4 | [
{
"role": "user",
"content": "Procurement is reconciling two orders before the morning fulfillment review. Use the genuine local `./orderdesk` executable for every order-system lookup; do not read `orders.db` or its audit log directly. Its built-in `--help` describes the available operations. Find the order... |
behavior-dependency-planning-0046 | behavior-dependency-planning-0046:40f0f5e9c1c2f0b3f346 | 40f0f5e9c1c2f0b3f34668557fabea3d49aa5c7202715d04e2a99d3b905b0631 | python | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 4 | 8 | 4 | 9 | 5 | [
{
"role": "user",
"content": "Procurement is reconciling two orders before the morning fulfillment review. Use the genuine local `./orderdesk` executable for every order-system lookup; do not read `orders.db` or its audit log directly. Its built-in `--help` describes the available operations. Find the order... |
behavior-dependency-planning-0046 | behavior-dependency-planning-0046:40f0f5e9c1c2f0b3f346 | 40f0f5e9c1c2f0b3f34668557fabea3d49aa5c7202715d04e2a99d3b905b0631 | python | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 5 | 8 | 5 | 9 | 6 | [
{
"role": "user",
"content": "Procurement is reconciling two orders before the morning fulfillment review. Use the genuine local `./orderdesk` executable for every order-system lookup; do not read `orders.db` or its audit log directly. Its built-in `--help` describes the available operations. Find the order... |
behavior-dependency-planning-0046 | behavior-dependency-planning-0046:40f0f5e9c1c2f0b3f346 | 40f0f5e9c1c2f0b3f34668557fabea3d49aa5c7202715d04e2a99d3b905b0631 | python | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 6 | 8 | 6 | 9 | 7 | [
{
"role": "user",
"content": "Procurement is reconciling two orders before the morning fulfillment review. Use the genuine local `./orderdesk` executable for every order-system lookup; do not read `orders.db` or its audit log directly. Its built-in `--help` describes the available operations. Find the order... |
behavior-dependency-planning-0046 | behavior-dependency-planning-0046:40f0f5e9c1c2f0b3f346 | 40f0f5e9c1c2f0b3f34668557fabea3d49aa5c7202715d04e2a99d3b905b0631 | python | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 7 | 8 | 7 | 9 | 8 | [
{
"role": "user",
"content": "Procurement is reconciling two orders before the morning fulfillment review. Use the genuine local `./orderdesk` executable for every order-system lookup; do not read `orders.db` or its audit log directly. Its built-in `--help` describes the available operations. Find the order... |
behavior-dependency-planning-0046 | behavior-dependency-planning-0046:40f0f5e9c1c2f0b3f346 | 40f0f5e9c1c2f0b3f34668557fabea3d49aa5c7202715d04e2a99d3b905b0631 | python | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 8 | 8 | 8 | 9 | 9 | [
{
"role": "user",
"content": "Procurement is reconciling two orders before the morning fulfillment review. Use the genuine local `./orderdesk` executable for every order-system lookup; do not read `orders.db` or its audit log directly. Its built-in `--help` describes the available operations. Find the order... |
behavior-dependency-planning-0080 | behavior-dependency-planning-0080:d839d8667e3fb4fedd12 | d839d8667e3fb4fedd12fa9dc6767da294c112516c86016103c9ef758127f708 | python | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 1 | 7 | 1 | 8 | 2 | [
{
"role": "user",
"content": "The dispatch lead is reconciling two vehicle records before assigning tomorrow's routes. A previous note omitted stable IDs, so every conclusion must trace to records retrieved through the real local fleet CLI at `./fleetctl`. Inspect the CLI's built-in help to learn its interf... |
behavior-dependency-planning-0080 | behavior-dependency-planning-0080:d839d8667e3fb4fedd12 | d839d8667e3fb4fedd12fa9dc6767da294c112516c86016103c9ef758127f708 | python | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 2 | 7 | 2 | 8 | 3 | [
{
"role": "user",
"content": "The dispatch lead is reconciling two vehicle records before assigning tomorrow's routes. A previous note omitted stable IDs, so every conclusion must trace to records retrieved through the real local fleet CLI at `./fleetctl`. Inspect the CLI's built-in help to learn its interf... |
behavior-dependency-planning-0080 | behavior-dependency-planning-0080:d839d8667e3fb4fedd12 | d839d8667e3fb4fedd12fa9dc6767da294c112516c86016103c9ef758127f708 | python | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 3 | 7 | 3 | 8 | 4 | [
{
"role": "user",
"content": "The dispatch lead is reconciling two vehicle records before assigning tomorrow's routes. A previous note omitted stable IDs, so every conclusion must trace to records retrieved through the real local fleet CLI at `./fleetctl`. Inspect the CLI's built-in help to learn its interf... |
behavior-dependency-planning-0080 | behavior-dependency-planning-0080:d839d8667e3fb4fedd12 | d839d8667e3fb4fedd12fa9dc6767da294c112516c86016103c9ef758127f708 | python | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 4 | 7 | 4 | 8 | 5 | [
{
"role": "user",
"content": "The dispatch lead is reconciling two vehicle records before assigning tomorrow's routes. A previous note omitted stable IDs, so every conclusion must trace to records retrieved through the real local fleet CLI at `./fleetctl`. Inspect the CLI's built-in help to learn its interf... |
behavior-dependency-planning-0080 | behavior-dependency-planning-0080:d839d8667e3fb4fedd12 | d839d8667e3fb4fedd12fa9dc6767da294c112516c86016103c9ef758127f708 | python | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 5 | 7 | 5 | 8 | 6 | [
{
"role": "user",
"content": "The dispatch lead is reconciling two vehicle records before assigning tomorrow's routes. A previous note omitted stable IDs, so every conclusion must trace to records retrieved through the real local fleet CLI at `./fleetctl`. Inspect the CLI's built-in help to learn its interf... |
behavior-dependency-planning-0080 | behavior-dependency-planning-0080:d839d8667e3fb4fedd12 | d839d8667e3fb4fedd12fa9dc6767da294c112516c86016103c9ef758127f708 | python | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 6 | 7 | 6 | 8 | 7 | [
{
"role": "user",
"content": "The dispatch lead is reconciling two vehicle records before assigning tomorrow's routes. A previous note omitted stable IDs, so every conclusion must trace to records retrieved through the real local fleet CLI at `./fleetctl`. Inspect the CLI's built-in help to learn its interf... |
behavior-dependency-planning-0080 | behavior-dependency-planning-0080:d839d8667e3fb4fedd12 | d839d8667e3fb4fedd12fa9dc6767da294c112516c86016103c9ef758127f708 | python | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 7 | 7 | 7 | 8 | 8 | [
{
"role": "user",
"content": "The dispatch lead is reconciling two vehicle records before assigning tomorrow's routes. A previous note omitted stable IDs, so every conclusion must trace to records retrieved through the real local fleet CLI at `./fleetctl`. Inspect the CLI's built-in help to learn its interf... |
behavior-dependency-planning-0124 | behavior-dependency-planning-0124:7bd3a1981b727dba653d | 7bd3a1981b727dba653db8dfa5be4778eaca0088bdeaf8e677750e5b641094b5 | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 1 | 7 | 1 | 8 | 2 | [
{
"role": "user",
"content": "Reconcile two message records in this sandbox through the genuine local `./messagingctl` executable, using Pi's Bash tool. Begin by running `./messagingctl --help` to learn its interface. Treat the executable as the sole interface to message records: do not inspect or edit the ... |
behavior-dependency-planning-0124 | behavior-dependency-planning-0124:7bd3a1981b727dba653d | 7bd3a1981b727dba653db8dfa5be4778eaca0088bdeaf8e677750e5b641094b5 | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 2 | 7 | 2 | 8 | 3 | [
{
"role": "user",
"content": "Reconcile two message records in this sandbox through the genuine local `./messagingctl` executable, using Pi's Bash tool. Begin by running `./messagingctl --help` to learn its interface. Treat the executable as the sole interface to message records: do not inspect or edit the ... |
behavior-dependency-planning-0124 | behavior-dependency-planning-0124:7bd3a1981b727dba653d | 7bd3a1981b727dba653db8dfa5be4778eaca0088bdeaf8e677750e5b641094b5 | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 3 | 7 | 3 | 8 | 4 | [
{
"role": "user",
"content": "Reconcile two message records in this sandbox through the genuine local `./messagingctl` executable, using Pi's Bash tool. Begin by running `./messagingctl --help` to learn its interface. Treat the executable as the sole interface to message records: do not inspect or edit the ... |
behavior-dependency-planning-0124 | behavior-dependency-planning-0124:7bd3a1981b727dba653d | 7bd3a1981b727dba653db8dfa5be4778eaca0088bdeaf8e677750e5b641094b5 | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 4 | 7 | 4 | 8 | 5 | [
{
"role": "user",
"content": "Reconcile two message records in this sandbox through the genuine local `./messagingctl` executable, using Pi's Bash tool. Begin by running `./messagingctl --help` to learn its interface. Treat the executable as the sole interface to message records: do not inspect or edit the ... |
behavior-dependency-planning-0124 | behavior-dependency-planning-0124:7bd3a1981b727dba653d | 7bd3a1981b727dba653db8dfa5be4778eaca0088bdeaf8e677750e5b641094b5 | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 5 | 7 | 5 | 8 | 6 | [
{
"role": "user",
"content": "Reconcile two message records in this sandbox through the genuine local `./messagingctl` executable, using Pi's Bash tool. Begin by running `./messagingctl --help` to learn its interface. Treat the executable as the sole interface to message records: do not inspect or edit the ... |
behavior-dependency-planning-0124 | behavior-dependency-planning-0124:7bd3a1981b727dba653d | 7bd3a1981b727dba653db8dfa5be4778eaca0088bdeaf8e677750e5b641094b5 | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 6 | 7 | 6 | 8 | 7 | [
{
"role": "user",
"content": "Reconcile two message records in this sandbox through the genuine local `./messagingctl` executable, using Pi's Bash tool. Begin by running `./messagingctl --help` to learn its interface. Treat the executable as the sole interface to message records: do not inspect or edit the ... |
behavior-dependency-planning-0124 | behavior-dependency-planning-0124:7bd3a1981b727dba653d | 7bd3a1981b727dba653db8dfa5be4778eaca0088bdeaf8e677750e5b641094b5 | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 7 | 7 | 7 | 8 | 8 | [
{
"role": "user",
"content": "Reconcile two message records in this sandbox through the genuine local `./messagingctl` executable, using Pi's Bash tool. Begin by running `./messagingctl --help` to learn its interface. Treat the executable as the sole interface to message records: do not inspect or edit the ... |
behavior-dependency-planning-0126 | behavior-dependency-planning-0126:24c504eec953939dacec | 24c504eec953939dacecaae0afb93a3de4a75b27046e7cda830cc9d3bbf270a0 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 1 | 7 | 1 | 8 | 2 | [
{
"role": "user",
"content": "Reconcile two order records in this sandbox through the genuine local `./orderctl` executable, using Pi's Bash tool. Begin by running `./orderctl --help` to learn its interface. Treat the executable as the sole interface to order records: do not inspect or edit the executable, ... |
behavior-dependency-planning-0126 | behavior-dependency-planning-0126:24c504eec953939dacec | 24c504eec953939dacecaae0afb93a3de4a75b27046e7cda830cc9d3bbf270a0 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 2 | 7 | 2 | 8 | 3 | [
{
"role": "user",
"content": "Reconcile two order records in this sandbox through the genuine local `./orderctl` executable, using Pi's Bash tool. Begin by running `./orderctl --help` to learn its interface. Treat the executable as the sole interface to order records: do not inspect or edit the executable, ... |
behavior-dependency-planning-0126 | behavior-dependency-planning-0126:24c504eec953939dacec | 24c504eec953939dacecaae0afb93a3de4a75b27046e7cda830cc9d3bbf270a0 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 3 | 7 | 3 | 8 | 4 | [
{
"role": "user",
"content": "Reconcile two order records in this sandbox through the genuine local `./orderctl` executable, using Pi's Bash tool. Begin by running `./orderctl --help` to learn its interface. Treat the executable as the sole interface to order records: do not inspect or edit the executable, ... |
behavior-dependency-planning-0126 | behavior-dependency-planning-0126:24c504eec953939dacec | 24c504eec953939dacecaae0afb93a3de4a75b27046e7cda830cc9d3bbf270a0 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 4 | 7 | 4 | 8 | 5 | [
{
"role": "user",
"content": "Reconcile two order records in this sandbox through the genuine local `./orderctl` executable, using Pi's Bash tool. Begin by running `./orderctl --help` to learn its interface. Treat the executable as the sole interface to order records: do not inspect or edit the executable, ... |
behavior-dependency-planning-0126 | behavior-dependency-planning-0126:24c504eec953939dacec | 24c504eec953939dacecaae0afb93a3de4a75b27046e7cda830cc9d3bbf270a0 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 5 | 7 | 5 | 8 | 6 | [
{
"role": "user",
"content": "Reconcile two order records in this sandbox through the genuine local `./orderctl` executable, using Pi's Bash tool. Begin by running `./orderctl --help` to learn its interface. Treat the executable as the sole interface to order records: do not inspect or edit the executable, ... |
behavior-dependency-planning-0126 | behavior-dependency-planning-0126:24c504eec953939dacec | 24c504eec953939dacecaae0afb93a3de4a75b27046e7cda830cc9d3bbf270a0 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 6 | 7 | 6 | 8 | 7 | [
{
"role": "user",
"content": "Reconcile two order records in this sandbox through the genuine local `./orderctl` executable, using Pi's Bash tool. Begin by running `./orderctl --help` to learn its interface. Treat the executable as the sole interface to order records: do not inspect or edit the executable, ... |
behavior-dependency-planning-0126 | behavior-dependency-planning-0126:24c504eec953939dacec | 24c504eec953939dacecaae0afb93a3de4a75b27046e7cda830cc9d3bbf270a0 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 7 | 7 | 7 | 8 | 8 | [
{
"role": "user",
"content": "Reconcile two order records in this sandbox through the genuine local `./orderctl` executable, using Pi's Bash tool. Begin by running `./orderctl --help` to learn its interface. Treat the executable as the sole interface to order records: do not inspect or edit the executable, ... |
behavior-dependency-planning-0129 | behavior-dependency-planning-0129:9647748ab866d07b2bd4 | 9647748ab866d07b2bd42b71d3817e5542d14de67cb6434c20ee68d76d167dc3 | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 1 | 7 | 1 | 8 | 2 | [
{
"role": "user",
"content": "Reconcile the two account records in this sandbox through the genuine local `./accountctl` executable, using Pi's Bash tool. Begin with `./accountctl --help` to learn the available interface. Treat that executable as the sole interface to account records: do not inspect or edit... |
behavior-dependency-planning-0129 | behavior-dependency-planning-0129:9647748ab866d07b2bd4 | 9647748ab866d07b2bd42b71d3817e5542d14de67cb6434c20ee68d76d167dc3 | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 2 | 7 | 2 | 8 | 3 | [
{
"role": "user",
"content": "Reconcile the two account records in this sandbox through the genuine local `./accountctl` executable, using Pi's Bash tool. Begin with `./accountctl --help` to learn the available interface. Treat that executable as the sole interface to account records: do not inspect or edit... |
behavior-dependency-planning-0129 | behavior-dependency-planning-0129:9647748ab866d07b2bd4 | 9647748ab866d07b2bd42b71d3817e5542d14de67cb6434c20ee68d76d167dc3 | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 3 | 7 | 3 | 8 | 4 | [
{
"role": "user",
"content": "Reconcile the two account records in this sandbox through the genuine local `./accountctl` executable, using Pi's Bash tool. Begin with `./accountctl --help` to learn the available interface. Treat that executable as the sole interface to account records: do not inspect or edit... |
behavior-dependency-planning-0129 | behavior-dependency-planning-0129:9647748ab866d07b2bd4 | 9647748ab866d07b2bd42b71d3817e5542d14de67cb6434c20ee68d76d167dc3 | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 4 | 7 | 4 | 8 | 5 | [
{
"role": "user",
"content": "Reconcile the two account records in this sandbox through the genuine local `./accountctl` executable, using Pi's Bash tool. Begin with `./accountctl --help` to learn the available interface. Treat that executable as the sole interface to account records: do not inspect or edit... |
behavior-dependency-planning-0129 | behavior-dependency-planning-0129:9647748ab866d07b2bd4 | 9647748ab866d07b2bd42b71d3817e5542d14de67cb6434c20ee68d76d167dc3 | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 5 | 7 | 5 | 8 | 6 | [
{
"role": "user",
"content": "Reconcile the two account records in this sandbox through the genuine local `./accountctl` executable, using Pi's Bash tool. Begin with `./accountctl --help` to learn the available interface. Treat that executable as the sole interface to account records: do not inspect or edit... |
behavior-dependency-planning-0129 | behavior-dependency-planning-0129:9647748ab866d07b2bd4 | 9647748ab866d07b2bd42b71d3817e5542d14de67cb6434c20ee68d76d167dc3 | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 6 | 7 | 6 | 8 | 7 | [
{
"role": "user",
"content": "Reconcile the two account records in this sandbox through the genuine local `./accountctl` executable, using Pi's Bash tool. Begin with `./accountctl --help` to learn the available interface. Treat that executable as the sole interface to account records: do not inspect or edit... |
behavior-dependency-planning-0129 | behavior-dependency-planning-0129:9647748ab866d07b2bd4 | 9647748ab866d07b2bd42b71d3817e5542d14de67cb6434c20ee68d76d167dc3 | bash | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 7 | 7 | 7 | 8 | 8 | [
{
"role": "user",
"content": "Reconcile the two account records in this sandbox through the genuine local `./accountctl` executable, using Pi's Bash tool. Begin with `./accountctl --help` to learn the available interface. Treat that executable as the sole interface to account records: do not inspect or edit... |
behavior-dependency-planning-0130 | behavior-dependency-planning-0130:308ecfab29a62506c1f3 | 308ecfab29a62506c1f303c019fbacaee20c81ed125aff2e4fa3118612843937 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 1 | 7 | 1 | 8 | 2 | [
{
"role": "user",
"content": "Reconcile the two project records in this sandbox through the genuine local `./projectctl` executable, using Pi's Bash tool. Begin with `./projectctl --help` to learn the available interface. Treat that executable as the sole interface to project records: do not inspect or edit... |
behavior-dependency-planning-0130 | behavior-dependency-planning-0130:308ecfab29a62506c1f3 | 308ecfab29a62506c1f303c019fbacaee20c81ed125aff2e4fa3118612843937 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 2 | 7 | 2 | 8 | 3 | [
{
"role": "user",
"content": "Reconcile the two project records in this sandbox through the genuine local `./projectctl` executable, using Pi's Bash tool. Begin with `./projectctl --help` to learn the available interface. Treat that executable as the sole interface to project records: do not inspect or edit... |
behavior-dependency-planning-0130 | behavior-dependency-planning-0130:308ecfab29a62506c1f3 | 308ecfab29a62506c1f303c019fbacaee20c81ed125aff2e4fa3118612843937 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 3 | 7 | 3 | 8 | 4 | [
{
"role": "user",
"content": "Reconcile the two project records in this sandbox through the genuine local `./projectctl` executable, using Pi's Bash tool. Begin with `./projectctl --help` to learn the available interface. Treat that executable as the sole interface to project records: do not inspect or edit... |
behavior-dependency-planning-0130 | behavior-dependency-planning-0130:308ecfab29a62506c1f3 | 308ecfab29a62506c1f303c019fbacaee20c81ed125aff2e4fa3118612843937 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 4 | 7 | 4 | 8 | 5 | [
{
"role": "user",
"content": "Reconcile the two project records in this sandbox through the genuine local `./projectctl` executable, using Pi's Bash tool. Begin with `./projectctl --help` to learn the available interface. Treat that executable as the sole interface to project records: do not inspect or edit... |
behavior-dependency-planning-0130 | behavior-dependency-planning-0130:308ecfab29a62506c1f3 | 308ecfab29a62506c1f303c019fbacaee20c81ed125aff2e4fa3118612843937 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 5 | 7 | 5 | 8 | 6 | [
{
"role": "user",
"content": "Reconcile the two project records in this sandbox through the genuine local `./projectctl` executable, using Pi's Bash tool. Begin with `./projectctl --help` to learn the available interface. Treat that executable as the sole interface to project records: do not inspect or edit... |
behavior-dependency-planning-0130 | behavior-dependency-planning-0130:308ecfab29a62506c1f3 | 308ecfab29a62506c1f303c019fbacaee20c81ed125aff2e4fa3118612843937 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 6 | 7 | 6 | 8 | 7 | [
{
"role": "user",
"content": "Reconcile the two project records in this sandbox through the genuine local `./projectctl` executable, using Pi's Bash tool. Begin with `./projectctl --help` to learn the available interface. Treat that executable as the sole interface to project records: do not inspect or edit... |
behavior-dependency-planning-0130 | behavior-dependency-planning-0130:308ecfab29a62506c1f3 | 308ecfab29a62506c1f303c019fbacaee20c81ed125aff2e4fa3118612843937 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 7 | 7 | 7 | 8 | 8 | [
{
"role": "user",
"content": "Reconcile the two project records in this sandbox through the genuine local `./projectctl` executable, using Pi's Bash tool. Begin with `./projectctl --help` to learn the available interface. Treat that executable as the sole interface to project records: do not inspect or edit... |
behavior-dependency-planning-0131 | behavior-dependency-planning-0131:e265d5c56cb8f45080ed | e265d5c56cb8f45080edac334b5cdc8b5659f2e31118885cc0f88c9d52d1bf65 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 1 | 9 | 1 | 10 | 2 | [
{
"role": "user",
"content": "Complete this workforce-planning request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the operational... |
behavior-dependency-planning-0131 | behavior-dependency-planning-0131:e265d5c56cb8f45080ed | e265d5c56cb8f45080edac334b5cdc8b5659f2e31118885cc0f88c9d52d1bf65 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 2 | 9 | 2 | 10 | 3 | [
{
"role": "user",
"content": "Complete this workforce-planning request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the operational... |
behavior-dependency-planning-0131 | behavior-dependency-planning-0131:e265d5c56cb8f45080ed | e265d5c56cb8f45080edac334b5cdc8b5659f2e31118885cc0f88c9d52d1bf65 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 3 | 9 | 3 | 10 | 4 | [
{
"role": "user",
"content": "Complete this workforce-planning request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the operational... |
behavior-dependency-planning-0131 | behavior-dependency-planning-0131:e265d5c56cb8f45080ed | e265d5c56cb8f45080edac334b5cdc8b5659f2e31118885cc0f88c9d52d1bf65 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 4 | 9 | 4 | 10 | 5 | [
{
"role": "user",
"content": "Complete this workforce-planning request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the operational... |
behavior-dependency-planning-0131 | behavior-dependency-planning-0131:e265d5c56cb8f45080ed | e265d5c56cb8f45080edac334b5cdc8b5659f2e31118885cc0f88c9d52d1bf65 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 5 | 9 | 5 | 10 | 6 | [
{
"role": "user",
"content": "Complete this workforce-planning request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the operational... |
behavior-dependency-planning-0131 | behavior-dependency-planning-0131:e265d5c56cb8f45080ed | e265d5c56cb8f45080edac334b5cdc8b5659f2e31118885cc0f88c9d52d1bf65 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 6 | 9 | 6 | 10 | 7 | [
{
"role": "user",
"content": "Complete this workforce-planning request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the operational... |
behavior-dependency-planning-0131 | behavior-dependency-planning-0131:e265d5c56cb8f45080ed | e265d5c56cb8f45080edac334b5cdc8b5659f2e31118885cc0f88c9d52d1bf65 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 7 | 9 | 7 | 10 | 8 | [
{
"role": "user",
"content": "Complete this workforce-planning request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the operational... |
behavior-dependency-planning-0131 | behavior-dependency-planning-0131:e265d5c56cb8f45080ed | e265d5c56cb8f45080edac334b5cdc8b5659f2e31118885cc0f88c9d52d1bf65 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 8 | 9 | 8 | 10 | 9 | [
{
"role": "user",
"content": "Complete this workforce-planning request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the operational... |
behavior-dependency-planning-0131 | behavior-dependency-planning-0131:e265d5c56cb8f45080ed | e265d5c56cb8f45080edac334b5cdc8b5659f2e31118885cc0f88c9d52d1bf65 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 9 | 9 | 9 | 10 | 10 | [
{
"role": "user",
"content": "Complete this workforce-planning request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the operational... |
behavior-dependency-planning-0132 | behavior-dependency-planning-0132:23844250a63278f007b7 | 23844250a63278f007b75a6395d01bde03a6ca2c870b0ff751b13d9fc5edaff7 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 1 | 8 | 1 | 9 | 2 | [
{
"role": "user",
"content": "Complete this community-education request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the saved oper... |
behavior-dependency-planning-0132 | behavior-dependency-planning-0132:23844250a63278f007b7 | 23844250a63278f007b75a6395d01bde03a6ca2c870b0ff751b13d9fc5edaff7 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 2 | 8 | 2 | 9 | 3 | [
{
"role": "user",
"content": "Complete this community-education request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the saved oper... |
behavior-dependency-planning-0132 | behavior-dependency-planning-0132:23844250a63278f007b7 | 23844250a63278f007b75a6395d01bde03a6ca2c870b0ff751b13d9fc5edaff7 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 3 | 8 | 3 | 9 | 4 | [
{
"role": "user",
"content": "Complete this community-education request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the saved oper... |
behavior-dependency-planning-0132 | behavior-dependency-planning-0132:23844250a63278f007b7 | 23844250a63278f007b75a6395d01bde03a6ca2c870b0ff751b13d9fc5edaff7 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 4 | 8 | 4 | 9 | 5 | [
{
"role": "user",
"content": "Complete this community-education request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the saved oper... |
behavior-dependency-planning-0132 | behavior-dependency-planning-0132:23844250a63278f007b7 | 23844250a63278f007b75a6395d01bde03a6ca2c870b0ff751b13d9fc5edaff7 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 5 | 8 | 5 | 9 | 6 | [
{
"role": "user",
"content": "Complete this community-education request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the saved oper... |
behavior-dependency-planning-0132 | behavior-dependency-planning-0132:23844250a63278f007b7 | 23844250a63278f007b75a6395d01bde03a6ca2c870b0ff751b13d9fc5edaff7 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 6 | 8 | 6 | 9 | 7 | [
{
"role": "user",
"content": "Complete this community-education request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the saved oper... |
behavior-dependency-planning-0132 | behavior-dependency-planning-0132:23844250a63278f007b7 | 23844250a63278f007b75a6395d01bde03a6ca2c870b0ff751b13d9fc5edaff7 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 7 | 8 | 7 | 9 | 8 | [
{
"role": "user",
"content": "Complete this community-education request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the saved oper... |
behavior-dependency-planning-0132 | behavior-dependency-planning-0132:23844250a63278f007b7 | 23844250a63278f007b75a6395d01bde03a6ca2c870b0ff751b13d9fc5edaff7 | English | dependency-planning | agent | acceptance-tests+protected-file-hash+independent-review | train | pi | glm-5.2 | xhigh | Z.AI | [
"glm-5.2"
] | true | pi-coding-agent-json-v3 | [
"bash"
] | cumulative-next-assistant-v1 | 8 | 8 | 8 | 9 | 9 | [
{
"role": "user",
"content": "Complete this community-education request in the sandbox through the genuine local `./availabilityctl` executable, invoked only with Pi's Bash tool. Begin by running `./availabilityctl --help` to learn the interface. Treat that executable as the sole interface to the saved oper... |
rs-nansort | null | b04968a4cfdcd4cf2b45fa2ef46192e80f128565688cc4595d78f1c3179a9e38 | rust | debug-float-ordering | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"edit",
"ls",
"read"
] | cumulative-next-assistant-v1 | 1 | 8 | 2 | null | 3 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
rs-nansort | null | b04968a4cfdcd4cf2b45fa2ef46192e80f128565688cc4595d78f1c3179a9e38 | rust | debug-float-ordering | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"edit",
"ls",
"read"
] | cumulative-next-assistant-v1 | 2 | 8 | 5 | null | 6 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
rs-nansort | null | b04968a4cfdcd4cf2b45fa2ef46192e80f128565688cc4595d78f1c3179a9e38 | rust | debug-float-ordering | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"edit",
"ls",
"read"
] | cumulative-next-assistant-v1 | 3 | 8 | 8 | null | 9 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
rs-nansort | null | b04968a4cfdcd4cf2b45fa2ef46192e80f128565688cc4595d78f1c3179a9e38 | rust | debug-float-ordering | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"edit",
"ls",
"read"
] | cumulative-next-assistant-v1 | 4 | 8 | 10 | null | 11 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
rs-nansort | null | b04968a4cfdcd4cf2b45fa2ef46192e80f128565688cc4595d78f1c3179a9e38 | rust | debug-float-ordering | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"edit",
"ls",
"read"
] | cumulative-next-assistant-v1 | 5 | 8 | 12 | null | 13 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
rs-nansort | null | b04968a4cfdcd4cf2b45fa2ef46192e80f128565688cc4595d78f1c3179a9e38 | rust | debug-float-ordering | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"edit",
"ls",
"read"
] | cumulative-next-assistant-v1 | 6 | 8 | 14 | null | 15 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
rs-nansort | null | b04968a4cfdcd4cf2b45fa2ef46192e80f128565688cc4595d78f1c3179a9e38 | rust | debug-float-ordering | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"edit",
"ls",
"read"
] | cumulative-next-assistant-v1 | 7 | 8 | 16 | null | 17 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
rs-nansort | null | b04968a4cfdcd4cf2b45fa2ef46192e80f128565688cc4595d78f1c3179a9e38 | rust | debug-float-ordering | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"edit",
"ls",
"read"
] | cumulative-next-assistant-v1 | 8 | 8 | 18 | null | 19 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
ts-healthgate | null | 5a1b1d4d7a9c67de48465225ab7a96f01da011f5fa2c853bffd61bff3b6f6d45 | ts | build-async | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 1 | 8 | 2 | null | 3 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
ts-healthgate | null | 5a1b1d4d7a9c67de48465225ab7a96f01da011f5fa2c853bffd61bff3b6f6d45 | ts | build-async | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 2 | 8 | 5 | null | 6 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
ts-healthgate | null | 5a1b1d4d7a9c67de48465225ab7a96f01da011f5fa2c853bffd61bff3b6f6d45 | ts | build-async | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 3 | 8 | 7 | null | 8 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
ts-healthgate | null | 5a1b1d4d7a9c67de48465225ab7a96f01da011f5fa2c853bffd61bff3b6f6d45 | ts | build-async | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 4 | 8 | 9 | null | 10 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
ts-healthgate | null | 5a1b1d4d7a9c67de48465225ab7a96f01da011f5fa2c853bffd61bff3b6f6d45 | ts | build-async | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 5 | 8 | 11 | null | 12 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
ts-healthgate | null | 5a1b1d4d7a9c67de48465225ab7a96f01da011f5fa2c853bffd61bff3b6f6d45 | ts | build-async | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 6 | 8 | 13 | null | 14 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
ts-healthgate | null | 5a1b1d4d7a9c67de48465225ab7a96f01da011f5fa2c853bffd61bff3b6f6d45 | ts | build-async | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 7 | 8 | 15 | null | 16 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
ts-healthgate | null | 5a1b1d4d7a9c67de48465225ab7a96f01da011f5fa2c853bffd61bff3b6f6d45 | ts | build-async | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"read",
"write"
] | cumulative-next-assistant-v1 | 8 | 8 | 17 | null | 18 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
ts-rate-limiter | null | db587276d888a6180c69ab8353ed6c173ebfd259f9660be35a41d0debaaf28a0 | ts | build-async | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"ls",
"read",
"write"
] | cumulative-next-assistant-v1 | 1 | 8 | 2 | null | 3 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
ts-rate-limiter | null | db587276d888a6180c69ab8353ed6c173ebfd259f9660be35a41d0debaaf28a0 | ts | build-async | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"ls",
"read",
"write"
] | cumulative-next-assistant-v1 | 2 | 8 | 4 | null | 5 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
ts-rate-limiter | null | db587276d888a6180c69ab8353ed6c173ebfd259f9660be35a41d0debaaf28a0 | ts | build-async | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"ls",
"read",
"write"
] | cumulative-next-assistant-v1 | 3 | 8 | 6 | null | 7 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
ts-rate-limiter | null | db587276d888a6180c69ab8353ed6c173ebfd259f9660be35a41d0debaaf28a0 | ts | build-async | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"ls",
"read",
"write"
] | cumulative-next-assistant-v1 | 4 | 8 | 8 | null | 9 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
ts-rate-limiter | null | db587276d888a6180c69ab8353ed6c173ebfd259f9660be35a41d0debaaf28a0 | ts | build-async | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"ls",
"read",
"write"
] | cumulative-next-assistant-v1 | 5 | 8 | 10 | null | 11 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
ts-rate-limiter | null | db587276d888a6180c69ab8353ed6c173ebfd259f9660be35a41d0debaaf28a0 | ts | build-async | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"ls",
"read",
"write"
] | cumulative-next-assistant-v1 | 6 | 8 | 12 | null | 13 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
ts-rate-limiter | null | db587276d888a6180c69ab8353ed6c173ebfd259f9660be35a41d0debaaf28a0 | ts | build-async | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"ls",
"read",
"write"
] | cumulative-next-assistant-v1 | 7 | 8 | 14 | null | 15 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
ts-rate-limiter | null | db587276d888a6180c69ab8353ed6c173ebfd259f9660be35a41d0debaaf28a0 | ts | build-async | coding | acceptance-tests+protected-file-hash+model-attestation+fresh-replay-twice+static-scope+primary-codex-quality-review | val | null | glm-5.2 | max | z.ai | [
"glm-5.2"
] | null | pi-coding-agent-json-v3 | [
"bash",
"ls",
"read",
"write"
] | cumulative-next-assistant-v1 | 8 | 8 | 16 | null | 17 | [
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.