File size: 36,110 Bytes
81e5fe7 0721bb4 81e5fe7 0721bb4 81e5fe7 0721bb4 81e5fe7 0721bb4 81e5fe7 0721bb4 81e5fe7 0721bb4 81e5fe7 0721bb4 81e5fe7 0721bb4 81e5fe7 0721bb4 81e5fe7 0721bb4 81e5fe7 0721bb4 81e5fe7 0721bb4 81e5fe7 0721bb4 81e5fe7 0721bb4 81e5fe7 0721bb4 81e5fe7 0721bb4 81e5fe7 0e5fdb5 49b0848 5a60e93 81e5fe7 0e5fdb5 49b0848 5a60e93 81e5fe7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 | """Few-shot examples for the planner prompt.
Two illustrative (question -> TaskList) pairs that teach the OUTPUT SHAPE:
stages, dependency edges, ordered tool-call chains, inline QueryIR,
"${t<id>}" placeholders, and the assumed data-flow convention — `retrieve_data`
pulls rows, then a composite `analyze_*` tool consumes them via a `data` placeholder
referencing the upstream result's column aliases (Pattern A; the tool team may
instead pick self-fetch by `source_id`, in which case these examples are reshaped
to match — see registry.py). They reference a hypothetical sales catalog
(`src_sales` / `t_orders`); these ids are part of the illustration and are not
validated against the user's real catalog. v1 is descriptive/diagnostic — no
modeling tasks.
See AGENT_ARCHITECTURE_CONTEXT_new.md §7.3 (Examples A and B).
"""
from __future__ import annotations
from .schemas import Task, TaskList, ToolCall
# --------------------------------------------------------------------------- #
# Example A — exploratory, no modeling.
# "Which product categories drove last quarter's revenue?"
# Shows: retrieve_data pulls rows -> analyze_aggregate sums revenue per
# category in one call (no manual per-category queries).
# --------------------------------------------------------------------------- #
_EXAMPLE_A = TaskList(
plan_id="example_a",
goal_restated="Identify which product categories contributed most to last quarter's revenue.",
assumptions=["'last quarter' = 2026-01-01 to 2026-03-31."],
open_questions=[],
tasks=[
Task(
id="t1",
stage="data_understanding",
objective="Confirm the sales source exposes category, revenue, and order date.",
tool_calls=[ToolCall(tool="check_data", args={"source_id": "src_sales"})],
expected_output="source_shape",
success_criteria="Produced the orders table schema; the 3 needed columns are present.",
depends_on=[],
estimated_cost="low",
),
Task(
id="t2",
stage="data_preparation",
objective="Pull last quarter's order-level category and revenue rows.",
tool_calls=[
ToolCall(
tool="retrieve_data",
args={
"ir": {
"source_id": "src_sales",
"table_id": "t_orders",
"select": [
{"kind": "column", "column_id": "c_category", "alias": "category"},
{"kind": "column", "column_id": "c_revenue", "alias": "revenue"},
],
"filters": [
{
"column_id": "c_order_date",
"op": "between",
"value": ["2026-01-01", "2026-03-31"],
"value_type": "date",
}
],
"limit": 10000,
}
},
)
],
expected_output="quarter_rows",
success_criteria="Produced last quarter's order rows with category and revenue.",
depends_on=["t1"],
estimated_cost="medium",
),
Task(
id="t3",
stage="evaluation",
objective="Sum revenue per category for the quarter.",
tool_calls=[
ToolCall(
tool="analyze_aggregate",
args={
"data": "${t2}",
"aggregations": {"revenue": ["sum"]},
"group_by": ["category"],
},
)
],
expected_output="category_revenue",
success_criteria="Produced total revenue per category, one row each.",
depends_on=["t2"],
estimated_cost="low",
),
],
)
# --------------------------------------------------------------------------- #
# Example B — descriptive / trend.
# "How has monthly revenue trended by region this year, and what's unusual?"
# --------------------------------------------------------------------------- #
_EXAMPLE_B = TaskList(
plan_id="example_b",
goal_restated="Describe this year's monthly revenue trend and flag unusual months.",
assumptions=["'this year' starts 2026-01-01."],
open_questions=["'Unusual' is interpreted as months far from the typical monthly revenue."],
tasks=[
Task(
id="t1",
stage="data_understanding",
objective="Confirm the sales source exposes order date, revenue, and region.",
tool_calls=[ToolCall(tool="check_data", args={"source_id": "src_sales"})],
expected_output="source_shape",
success_criteria="Produced the orders table schema; the needed columns are present.",
depends_on=[],
estimated_cost="low",
),
Task(
id="t2",
stage="data_preparation",
objective="Pull this year's order dates, revenue, and region.",
tool_calls=[
ToolCall(
tool="retrieve_data",
args={
"ir": {
"source_id": "src_sales",
"table_id": "t_orders",
"select": [
{
"kind": "column",
"column_id": "c_order_date",
"alias": "order_date",
},
{"kind": "column", "column_id": "c_revenue", "alias": "revenue"},
{"kind": "column", "column_id": "c_region", "alias": "region"},
],
"filters": [
{
"column_id": "c_order_date",
"op": ">=",
"value": "2026-01-01",
"value_type": "date",
}
],
"limit": 10000,
}
},
)
],
expected_output="ytd_rows",
success_criteria="Produced this year's order-level rows with date, revenue, region.",
depends_on=["t1"],
estimated_cost="medium",
),
Task(
id="t3",
stage="evaluation",
objective="Bucket revenue into months and summarize the trend and movement.",
tool_calls=[
ToolCall(
tool="analyze_trend",
args={
"data": "${t2}",
"date_column": "order_date",
"value_column": "revenue",
"freq": "month",
"agg": "sum",
},
)
],
expected_output="monthly_trend",
success_criteria=(
"Produced a per-month revenue series with direction and change rate to "
"flag months above/below the typical level."
),
depends_on=["t2"],
estimated_cost="low",
),
],
)
# --------------------------------------------------------------------------- #
# Example C — mixed structured + unstructured.
# "Revenue dipped in Q1 — what happened?"
# Shows: a structured branch (query -> analyze_trend) runs alongside an
# INDEPENDENT retrieve_knowledge branch that pulls qualitative context. Note
# retrieve_knowledge takes a natural-language `query` (NOT a `${t<id>}` data
# placeholder — it is a source, not a consumer) and can run in parallel; the
# Assembler folds the document context into the explanation.
# --------------------------------------------------------------------------- #
_EXAMPLE_C = TaskList(
plan_id="example_c",
goal_restated="Explain Q1's revenue dip using both the numbers and the qualitative record.",
assumptions=["'Q1' = 2026-01-01 to 2026-03-31."],
open_questions=[],
tasks=[
Task(
id="t1",
stage="data_understanding",
objective="Confirm the sales source exposes order date and revenue.",
tool_calls=[ToolCall(tool="check_data", args={"source_id": "src_sales"})],
expected_output="source_shape",
success_criteria="Produced the orders table schema; date and revenue columns present.",
depends_on=[],
estimated_cost="low",
),
Task(
id="t2",
stage="data_preparation",
objective="Pull Q1 order dates and revenue.",
tool_calls=[
ToolCall(
tool="retrieve_data",
args={
"ir": {
"source_id": "src_sales",
"table_id": "t_orders",
"select": [
{
"kind": "column",
"column_id": "c_order_date",
"alias": "order_date",
},
{"kind": "column", "column_id": "c_revenue", "alias": "revenue"},
],
"filters": [
{
"column_id": "c_order_date",
"op": "between",
"value": ["2026-01-01", "2026-03-31"],
"value_type": "date",
}
],
"limit": 10000,
}
},
)
],
expected_output="q1_rows",
success_criteria="Produced Q1 order rows with date and revenue.",
depends_on=["t1"],
estimated_cost="medium",
),
Task(
id="t3",
stage="evaluation",
objective="Summarize the Q1 monthly revenue trend to locate the dip.",
tool_calls=[
ToolCall(
tool="analyze_trend",
args={
"data": "${t2}",
"date_column": "order_date",
"value_column": "revenue",
"freq": "month",
"agg": "sum",
},
)
],
expected_output="q1_trend",
success_criteria="Produced a per-month revenue series showing where revenue fell.",
depends_on=["t2"],
estimated_cost="low",
),
Task(
id="t4",
stage="data_understanding",
objective="Retrieve qualitative context on Q1 operational events behind a dip.",
tool_calls=[
ToolCall(
tool="retrieve_knowledge",
args={
"query": "operational issues, outages, or notable events in Q1 2026",
"top_k": 5,
},
)
],
expected_output="q1_context_chunks",
success_criteria="Produced relevant document chunks about Q1 operations.",
depends_on=[],
estimated_cost="low",
),
],
)
# --------------------------------------------------------------------------- #
# Example D — group-by aggregation (analyze_aggregate arg shape).
# "What is the average and total order value per region?"
# Shows the EXACT analyze_aggregate args: `aggregations` is an OBJECT mapping each
# column to a LIST of functions ({"revenue": ["mean", "sum"]}), and `group_by` is a
# SEPARATE array — NOT a nested list of metric specs. Supported funcs: sum, mean,
# count, min, max, median, nunique.
# --------------------------------------------------------------------------- #
_EXAMPLE_D = TaskList(
plan_id="example_d",
goal_restated="Report the average and total order value for each region.",
assumptions=[],
open_questions=[],
tasks=[
Task(
id="t1",
stage="data_understanding",
objective="Confirm the sales source exposes region and revenue.",
tool_calls=[ToolCall(tool="check_data", args={"source_id": "src_sales"})],
expected_output="source_shape",
success_criteria="Produced the orders table schema; region and revenue present.",
depends_on=[],
estimated_cost="low",
),
Task(
id="t2",
stage="data_preparation",
objective="Pull order-level region and revenue.",
tool_calls=[
ToolCall(
tool="retrieve_data",
args={
"ir": {
"source_id": "src_sales",
"table_id": "t_orders",
"select": [
{"kind": "column", "column_id": "c_region", "alias": "region"},
{"kind": "column", "column_id": "c_revenue", "alias": "revenue"},
],
"limit": 10000,
}
},
)
],
expected_output="region_rows",
success_criteria="Produced order rows with region and revenue.",
depends_on=["t1"],
estimated_cost="medium",
),
Task(
id="t3",
stage="evaluation",
objective="Aggregate mean and total revenue per region.",
tool_calls=[
ToolCall(
tool="analyze_aggregate",
args={
"data": "${t2}",
"aggregations": {"revenue": ["mean", "sum"]},
"group_by": ["region"],
},
)
],
expected_output="region_aggregates",
success_criteria="Produced one row per region with mean and total revenue.",
depends_on=["t2"],
estimated_cost="low",
),
],
)
# --------------------------------------------------------------------------- #
# Example E — non-date filters (value_type is the ELEMENT type, never a container).
# "Total revenue for the East and West regions, counting orders of at least 100."
# Shows: an `in` filter over a list of strings uses value_type "string" (NOT
# "list"); a numeric comparison uses "decimal"; and every filter carries a
# value_type copied from the column's catalog [data_type].
# --------------------------------------------------------------------------- #
_EXAMPLE_E = TaskList(
plan_id="example_e",
goal_restated="Total revenue for the East and West regions, orders of at least 100.",
assumptions=["'at least 100' filters order revenue >= 100."],
open_questions=[],
tasks=[
Task(
id="t1",
stage="data_understanding",
objective="Confirm the sales source exposes region and revenue.",
tool_calls=[ToolCall(tool="check_data", args={"source_id": "src_sales"})],
expected_output="source_shape",
success_criteria="Produced the orders table schema; region and revenue present.",
depends_on=[],
estimated_cost="low",
),
Task(
id="t2",
stage="data_preparation",
objective="Pull East/West order rows of at least 100 with region and revenue.",
tool_calls=[
ToolCall(
tool="retrieve_data",
args={
"ir": {
"source_id": "src_sales",
"table_id": "t_orders",
"select": [
{"kind": "column", "column_id": "c_region", "alias": "region"},
{"kind": "column", "column_id": "c_revenue", "alias": "revenue"},
],
"filters": [
{
"column_id": "c_region",
"op": "in",
"value": ["East", "West"],
"value_type": "string",
},
{
"column_id": "c_revenue",
"op": ">=",
"value": 100,
"value_type": "decimal",
},
],
"limit": 10000,
}
},
)
],
expected_output="filtered_rows",
success_criteria="Produced East/West order rows above the revenue threshold.",
depends_on=["t1"],
estimated_cost="medium",
),
Task(
id="t3",
stage="evaluation",
objective="Sum revenue per region.",
tool_calls=[
ToolCall(
tool="analyze_aggregate",
args={
"data": "${t2}",
"aggregations": {"revenue": ["sum"]},
"group_by": ["region"],
},
)
],
expected_output="region_revenue",
success_criteria="Produced total revenue per region, one row each.",
depends_on=["t2"],
estimated_cost="low",
),
],
)
# --------------------------------------------------------------------------- #
# Example F — descriptive statistics (analyze_descriptive).
# "Give me the summary statistics for order revenue and quantity."
# Shows: retrieve_data pulls the numeric columns -> analyze_descriptive summarizes
# them. The `data` comes from the retrieve_data task (t2), NEVER from the check_data
# inspection step (t1) — check_data returns column metadata, not data rows.
# --------------------------------------------------------------------------- #
_EXAMPLE_F = TaskList(
plan_id="example_f",
goal_restated="Summarize the distribution of order revenue and quantity.",
assumptions=[],
open_questions=[],
tasks=[
Task(
id="t1",
stage="data_understanding",
objective="Confirm the sales source exposes order revenue and quantity.",
tool_calls=[ToolCall(tool="check_data", args={"source_id": "src_sales"})],
expected_output="source_shape",
success_criteria="Produced the orders table schema; the needed columns are present.",
depends_on=[],
estimated_cost="low",
),
Task(
id="t2",
stage="data_preparation",
objective="Pull the order revenue and quantity rows.",
tool_calls=[
ToolCall(
tool="retrieve_data",
args={
"ir": {
"source_id": "src_sales",
"table_id": "t_orders",
"select": [
{"kind": "column", "column_id": "c_revenue", "alias": "revenue"},
{"kind": "column", "column_id": "c_quantity", "alias": "quantity"},
],
"limit": 10000,
}
},
)
],
expected_output="order_rows",
success_criteria="Produced order-level rows with revenue and quantity.",
depends_on=["t1"],
estimated_cost="medium",
),
Task(
id="t3",
stage="evaluation",
objective="Summarize the distribution of revenue and quantity.",
tool_calls=[
ToolCall(
tool="analyze_descriptive",
args={
# `data` references t2 (retrieve_data rows), NOT t1 (check_data).
"data": "${t2}",
# column refs are the retrieve_data output aliases.
"column_ids": ["revenue", "quantity"],
},
)
],
expected_output="summary_stats",
success_criteria=(
"Produced mean/median/std/quartiles for revenue and quantity, above/below "
"the typical range."
),
depends_on=["t2"],
estimated_cost="low",
),
],
)
# --------------------------------------------------------------------------- #
# Example G — top-N ranking.
# "Top 3 product categories by total revenue."
# Shows: top-N is ONE retrieve_data query — group by the entity, aggregate the
# measure with an alias, order by that alias, limit N. NEVER a bare
# order-by-measure + limit (that ranks raw rows, so the same entity can appear
# twice — observed in production: "top 3 models" returned one model twice).
# --------------------------------------------------------------------------- #
_EXAMPLE_G = TaskList(
plan_id="example_g",
goal_restated="Rank product categories by total revenue and return the top 3.",
assumptions=[],
open_questions=[],
tasks=[
Task(
id="t1",
stage="data_understanding",
objective="Confirm the sales source exposes category and revenue.",
tool_calls=[ToolCall(tool="check_data", args={"source_id": "src_sales"})],
expected_output="source_shape",
success_criteria=(
"Produced the orders table schema; category and revenue columns "
"are present."
),
depends_on=[],
estimated_cost="low",
),
Task(
id="t2",
stage="data_preparation",
objective="Aggregate revenue per category, rank descending, keep the top 3.",
tool_calls=[
ToolCall(
tool="retrieve_data",
args={
"ir": {
"source_id": "src_sales",
"table_id": "t_orders",
"select": [
{"kind": "column", "column_id": "c_category", "alias": "category"},
{
"kind": "agg",
"fn": "sum",
"column_id": "c_revenue",
"alias": "total_revenue",
},
],
"group_by": ["c_category"],
"order_by": [{"column_id": "total_revenue", "dir": "desc"}],
"limit": 3,
}
},
)
],
expected_output="top3_categories",
success_criteria=(
"Produced at most 3 rows, one distinct category each, ranked by "
"total revenue."
),
depends_on=["t1"],
estimated_cost="low",
),
],
)
# --------------------------------------------------------------------------- #
# Example H — infeasible question (see planner.md "When the catalog cannot
# answer"). "What is our customer churn rate?" against a sales catalog with no
# subscription/churn data: no task list is forced onto unrelated columns;
# instead `infeasible_reason` states the gap + the nearest available data.
# --------------------------------------------------------------------------- #
_EXAMPLE_H = TaskList(
plan_id="example_h",
goal_restated="Measure the customer churn rate.",
assumptions=[],
open_questions=[],
tasks=[],
infeasible_reason=(
"The connected source has no churn or subscription-status data — the "
"orders table only carries order-level category, revenue, quantity, and "
"dates. Nearest available analyses: repeat-purchase behaviour or revenue "
"per customer over time."
),
)
# --------------------------------------------------------------------------- #
# Example I — combine two measures per entity (KM-703).
# "Which category has both the highest revenue and the highest average order
# quantity?" Shows: each measure is computed in its OWN grouped retrieve_data
# task (a "${t<id>}" placeholder resolves to a task's LAST output, so the two
# retrievals must be separate tasks), then analyze_merge aligns them on the
# shared entity alias. The merged table answers "both A and B" questions that
# a single query cannot express.
# --------------------------------------------------------------------------- #
_EXAMPLE_I = TaskList(
plan_id="example_i",
goal_restated=(
"Identify the product category with both the highest total revenue and the "
"highest average order quantity."
),
assumptions=[],
open_questions=[],
tasks=[
Task(
id="t1",
stage="data_understanding",
objective="Confirm the sales source exposes category, revenue, and quantity.",
tool_calls=[ToolCall(tool="check_data", args={"source_id": "src_sales"})],
expected_output="source_shape",
success_criteria=(
"Produced the orders table schema; category, revenue, and quantity "
"columns are present."
),
depends_on=[],
estimated_cost="low",
),
Task(
id="t2",
stage="data_preparation",
objective="Total revenue per category.",
tool_calls=[
ToolCall(
tool="retrieve_data",
args={
"ir": {
"source_id": "src_sales",
"table_id": "t_orders",
"select": [
{"kind": "column", "column_id": "c_category", "alias": "category"},
{
"kind": "agg",
"fn": "sum",
"column_id": "c_revenue",
"alias": "total_revenue",
},
],
"group_by": ["c_category"],
}
},
)
],
expected_output="revenue_per_category",
success_criteria="Produced one total-revenue row per category.",
depends_on=["t1"],
estimated_cost="low",
),
Task(
id="t3",
stage="data_preparation",
objective="Average order quantity per category.",
tool_calls=[
ToolCall(
tool="retrieve_data",
args={
"ir": {
"source_id": "src_sales",
"table_id": "t_orders",
"select": [
{"kind": "column", "column_id": "c_category", "alias": "category"},
{
"kind": "agg",
"fn": "avg",
"column_id": "c_quantity",
"alias": "avg_quantity",
},
],
"group_by": ["c_category"],
}
},
)
],
expected_output="quantity_per_category",
success_criteria="Produced one average-quantity row per category.",
depends_on=["t1"],
estimated_cost="low",
),
Task(
id="t4",
stage="evaluation",
objective="Align both measures per category to find the category leading on both.",
tool_calls=[
ToolCall(
tool="analyze_merge",
args={
"data": "${t2}",
"data_right": "${t3}",
"on": ["category"],
},
)
],
expected_output="combined_measures",
success_criteria=(
"Produced one row per category carrying both total_revenue and "
"avg_quantity."
),
depends_on=["t2", "t3"],
estimated_cost="low",
),
],
)
# --------------------------------------------------------------------------- #
# Example J — visualization tail (SPINE_V2_PLAN §4.3, recipe "viz tail").
# "Show me a bar chart of total revenue per product category."
# Shows: render_chart is planned ONLY on an explicit ask ("bar chart"), and is
# ALWAYS a tail step — its `data` consumes a TABLE-producing upstream (here the
# grouped top-N-style retrieve from Example G, without the limit), never stats/
# series/metadata. `x`/`y` reference that table's column aliases; the chart
# carries the already-aggregated rows (one bar per category), never raw order
# rows. The `assumptions` line carries the feasibility check on purpose: a chart
# ask never licenses aliasing a stand-in column (see Example K).
# --------------------------------------------------------------------------- #
_EXAMPLE_J = TaskList(
plan_id="example_j",
goal_restated="Chart total revenue per product category as a bar chart.",
assumptions=[
"The chart dimension exists in the catalog (c_category) — a chart ask is "
"planned only when the asked-for dimension and measure have real catalog "
"columns; otherwise it is infeasible, chart or no chart."
],
open_questions=[],
tasks=[
Task(
id="t1",
stage="data_understanding",
objective="Confirm the sales source exposes category and revenue.",
tool_calls=[ToolCall(tool="check_data", args={"source_id": "src_sales"})],
expected_output="source_shape",
success_criteria="Produced the orders table schema; category and revenue present.",
depends_on=[],
estimated_cost="low",
),
Task(
id="t2",
stage="data_preparation",
objective="Aggregate total revenue per product category.",
tool_calls=[
ToolCall(
tool="retrieve_data",
args={
"ir": {
"source_id": "src_sales",
"table_id": "t_orders",
"select": [
{"kind": "column", "column_id": "c_category", "alias": "category"},
{
"kind": "agg",
"fn": "sum",
"column_id": "c_revenue",
"alias": "total_revenue",
},
],
"group_by": ["c_category"],
}
},
)
],
expected_output="revenue_per_category",
success_criteria="Produced one total-revenue row per category.",
depends_on=["t1"],
estimated_cost="low",
),
Task(
id="t3",
stage="evaluation",
objective="Render the per-category revenue table as a bar chart.",
tool_calls=[
ToolCall(
tool="render_chart",
args={
# `data` references the TABLE task (t2) — a chart is always a
# tail on an aggregated table, never on raw rows or stats.
"data": "${t2}",
"chart_type": "bar",
"x": "category",
"y": "total_revenue",
"title": "Total revenue by product category",
},
)
],
expected_output="revenue_bar_chart",
success_criteria="Produced a bar-chart spec with one bar per category.",
depends_on=["t2"],
estimated_cost="low",
),
],
)
# --------------------------------------------------------------------------- #
# Example K — a chart ask that is INFEASIBLE (SPINE_V2_PLAN §4.3 + planner.md
# "Charts ... never relaxes feasibility"). "Plot the customer churn rate by
# month as a line chart" against the sales catalog: churn does not exist, and
# the explicit chart request does NOT license mapping some other column into
# the asked-for measure — the verdict is the same infeasible_reason Example H
# would give, chart or no chart.
# --------------------------------------------------------------------------- #
_EXAMPLE_K = TaskList(
plan_id="example_k",
goal_restated="Chart the monthly customer churn rate as a line chart.",
assumptions=[],
open_questions=[],
tasks=[],
infeasible_reason=(
"The connected source has no churn or subscription-status data — the "
"orders table only carries order-level category, revenue, quantity, and "
"dates — so there is nothing to chart. Nearest chartable analyses: "
"monthly revenue trend, or order counts per category."
),
)
EXAMPLES: list[tuple[str, TaskList]] = [
("Which product categories drove last quarter's revenue?", _EXAMPLE_A),
("How has monthly revenue trended by region this year, and what's unusual?", _EXAMPLE_B),
("Revenue dipped in Q1 — what happened?", _EXAMPLE_C),
("What is the average and total order value per region?", _EXAMPLE_D),
("Total revenue for the East and West regions, counting orders of at least 100.", _EXAMPLE_E),
("Give me the summary statistics for order revenue and quantity.", _EXAMPLE_F),
("Which 3 product categories have the best revenue performance?", _EXAMPLE_G),
("What is our customer churn rate?", _EXAMPLE_H),
(
"Which product category has both the highest revenue and the highest average "
"order quantity?",
_EXAMPLE_I,
),
("Show me a bar chart of total revenue per product category.", _EXAMPLE_J),
("Plot the customer churn rate by month as a line chart.", _EXAMPLE_K),
]
def render_examples() -> str:
"""Render the few-shots as text for the planner prompt."""
blocks: list[str] = []
for i, (question, plan) in enumerate(EXAMPLES, start=1):
blocks.append(
f"## Example {i}\n\n"
f"Question:\n{question}\n\n"
f"TaskList:\n{plan.model_dump_json(indent=2)}"
)
return "\n\n".join(blocks)
|