step.db_exec: add `returning` mode to capture rows from RETURNING clause by Copilot · Pull Request #300 · GoCodeAlone/workflow

Copilot · 2026-03-11T22:53:34Z

step.db_exec called db.Exec() unconditionally, discarding rows from PostgreSQL RETURNING clauses. The only workaround was semantically incorrect use of step.db_query for write operations.

Changes

DBExecStep: Added returning bool and mode string fields
Factory: Reads returning and mode from config; validates mode is "list" or "single" when returning: true (defaults to "list"); invalid values rejected at build time
Execute(): When returning: true, uses db.Query() and processes rows identically to step.db_query — mode: single → {row, found}, mode: list → {rows, count}; ignore_error continues to work in both modes
Tests: Single mode, list mode (multi-row UPDATE…RETURNING), and invalid-mode factory rejection
Docs: Updated step.db_exec table entry

Usage

- name: insert
  type: step.db_exec
  config:
    database: db
    query: >
      INSERT INTO items (id, name)
      VALUES (gen_random_uuid(), $1)
      RETURNING id, name, created_at
    params: ["{{.steps.parse.body.name}}"]
    returning: true
    mode: single   # output: {row: {...}, found: true}

Original prompt

This section details on the original issue you should resolve

<issue_title>step.db_exec: support RETURNING clause for insert/update operations</issue_title>
<issue_description>## Problem

step.db_exec is designed for INSERT/UPDATE/DELETE operations that don't return rows. However, PostgreSQL's RETURNING clause allows these operations to return the affected rows — which is essential for getting auto-generated values (IDs, timestamps, computed columns) without a separate SELECT query.

Currently, to get values back from an INSERT, you must either:

Use step.db_query instead of step.db_exec (works but semantically misleading — queries imply reads)

Perform the INSERT with step.db_exec then follow up with a separate step.db_query SELECT to fetch the generated values

Option 1 actually works today (we use it), but option 2 introduces race conditions and unnecessary round-trips.

Use Case

Common patterns that need RETURNING:
-- Get the auto-generated UUID and timestamps after insert
INSERT INTO follow_up_prompts (id, affiliate_id, name, ...)
VALUES (gen_random_uuid(), $1, $2, ...)
RETURNING id, created_at, updated_at;

-- Get the previous status after an update (for audit/state machine logic)
UPDATE orders SET status = 'shipped', updated_at = NOW()
WHERE id = $1
RETURNING id, status, updated_at;

-- Soft delete and return the deleted row
DELETE FROM sessions WHERE id = $1
RETURNING *;
Proposed Solution

Option A: step.db_exec gains a returning mode
- name: insert
  type: step.db_exec
  config:
    database: db
    query: >
      INSERT INTO items (id, name) VALUES (gen_random_uuid(), $1)
      RETURNING id, name, created_at
    params: ["{{.steps.parse.body.name}}"]
    returning: true    # switches from Exec() to Query(), returns rows
    mode: single       # like step.db_query — "single" returns {row, found}
When returning: true, the step internally uses Query() instead of Exec() and makes the returned rows available in the pipeline context, just like step.db_query.

Option B: Officially document step.db_query for writes

If the engine already supports using step.db_query for INSERT...RETURNING (which it does — we use it in production), document this as the intended pattern and ensure mode: single works correctly with write queries. The main concern is whether step.db_query applies any read-only optimizations or transaction isolation that would be wrong for write operations.

Current Workaround

We use step.db_query with mode: single for INSERT...RETURNING, which works but is semantically confusing — code reviewers expect db_query to be read-only. The step name implies a pure read operation.</issue_description>

Comments on the Issue (you are @copilot in this section)

Fixes step.db_exec: support RETURNING clause for insert/update operations #293

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

…g option Co-authored-by: intel352 <77607+intel352@users.noreply.github.com>

Copilot

Pull request overview

Adds an opt-in returning mode to step.db_exec so INSERT/UPDATE/DELETE statements that include a PostgreSQL-style RETURNING clause can return rows (avoiding the current workaround of using step.db_query for write operations).

Changes:

Extend DBExecStep + factory config parsing to support returning: true and mode: list|single (validated at build time).
Update DBExecStep.Execute() to use Query() and return rows/count or row/found outputs when returning is enabled.
Add tests for returning single/list behavior and invalid-mode rejection; update docs entry for step.db_exec.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 4 comments.

File	Description
module/pipeline_step_db_exec.go	Adds `returning` + `mode` config and implements row-returning execution path via `Query()` with db_query-like outputs.
module/pipeline_step_db_exec_test.go	Adds unit tests covering returning single/list modes and factory-time invalid mode validation.
DOCUMENTATION.md	Documents `step.db_exec` support for `returning: true` with `mode`.

module/pipeline_step_db_exec.go

DOCUMENTATION.md

module/pipeline_step_db_exec.go

intel352 · 2026-03-12T00:08:25Z

@copilot apply changes based on the comments in this thread

Build failing, lint failing, tests failing, config validation failing

github-actions · 2026-03-12T00:13:27Z

⏱ Benchmark Results

✅ No significant performance regressions detected.

benchstat comparison (baseline → PR)

## benchstat: baseline → PR
baseline-bench.txt:244: parsing iteration count: invalid syntax
baseline-bench.txt:312344: parsing iteration count: invalid syntax
baseline-bench.txt:639696: parsing iteration count: invalid syntax
baseline-bench.txt:934498: parsing iteration count: invalid syntax
baseline-bench.txt:1231892: parsing iteration count: invalid syntax
baseline-bench.txt:1537767: parsing iteration count: invalid syntax
benchmark-results.txt:244: parsing iteration count: invalid syntax
benchmark-results.txt:318629: parsing iteration count: invalid syntax
benchmark-results.txt:608985: parsing iteration count: invalid syntax
benchmark-results.txt:886855: parsing iteration count: invalid syntax
benchmark-results.txt:1189721: parsing iteration count: invalid syntax
benchmark-results.txt:1489650: parsing iteration count: invalid syntax
goos: linux
goarch: amd64
pkg: github.com/GoCodeAlone/workflow/dynamic
cpu: AMD EPYC 7763 64-Core Processor                
                            │ baseline-bench.txt │
                            │       sec/op       │
InterpreterCreation-4               7.651m ± 55%
ComponentLoad-4                     3.784m ±  3%
ComponentExecute-4                  2.066µ ±  1%
PoolContention/workers-1-4          1.135µ ±  3%
PoolContention/workers-2-4          1.148µ ±  1%
PoolContention/workers-4-4          1.148µ ±  1%
PoolContention/workers-8-4          1.141µ ±  2%
PoolContention/workers-16-4         1.134µ ±  2%
ComponentLifecycle-4                3.744m ±  3%
SourceValidation-4                  2.337µ ±  2%
RegistryConcurrent-4                770.2n ±  4%
LoaderLoadFromString-4              3.584m ±  1%
geomean                             19.37µ

                            │ baseline-bench.txt │
                            │        B/op        │
InterpreterCreation-4               1.944Mi ± 0%
ComponentLoad-4                     2.097Mi ± 0%
ComponentExecute-4                  1.203Ki ± 0%
PoolContention/workers-1-4          1.203Ki ± 0%
PoolContention/workers-2-4          1.203Ki ± 0%
PoolContention/workers-4-4          1.203Ki ± 0%
PoolContention/workers-8-4          1.203Ki ± 0%
PoolContention/workers-16-4         1.203Ki ± 0%
ComponentLifecycle-4                2.099Mi ± 0%
SourceValidation-4                  1.984Ki ± 0%
RegistryConcurrent-4                1.133Ki ± 0%
LoaderLoadFromString-4              2.099Mi ± 0%
geomean                             15.05Ki

                            │ baseline-bench.txt │
                            │     allocs/op      │
InterpreterCreation-4                15.09k ± 0%
ComponentLoad-4                      17.43k ± 0%
ComponentExecute-4                    25.00 ± 0%
PoolContention/workers-1-4            25.00 ± 0%
PoolContention/workers-2-4            25.00 ± 0%
PoolContention/workers-4-4            25.00 ± 0%
PoolContention/workers-8-4            25.00 ± 0%
PoolContention/workers-16-4           25.00 ± 0%
ComponentLifecycle-4                 17.48k ± 0%
SourceValidation-4                    32.00 ± 0%
RegistryConcurrent-4                  2.000 ± 0%
LoaderLoadFromString-4               17.47k ± 0%
geomean                               181.2

cpu: AMD EPYC 9V74 80-Core Processor                
                            │ benchmark-results.txt │
                            │        sec/op         │
InterpreterCreation-4                  5.962m ± 69%
ComponentLoad-4                        3.441m ±  1%
ComponentExecute-4                     1.949µ ±  0%
PoolContention/workers-1-4             1.047µ ±  5%
PoolContention/workers-2-4             1.047µ ±  1%
PoolContention/workers-4-4             1.044µ ±  1%
PoolContention/workers-8-4             1.052µ ±  1%
PoolContention/workers-16-4            1.056µ ±  2%
ComponentLifecycle-4                   3.449m ±  0%
SourceValidation-4                     2.133µ ±  1%
RegistryConcurrent-4                   834.0n ±  3%
LoaderLoadFromString-4                 3.505m ±  1%
geomean                                17.91µ

                            │ benchmark-results.txt │
                            │         B/op          │
InterpreterCreation-4                  1.944Mi ± 0%
ComponentLoad-4                        2.097Mi ± 0%
ComponentExecute-4                     1.203Ki ± 0%
PoolContention/workers-1-4             1.203Ki ± 0%
PoolContention/workers-2-4             1.203Ki ± 0%
PoolContention/workers-4-4             1.203Ki ± 0%
PoolContention/workers-8-4             1.203Ki ± 0%
PoolContention/workers-16-4            1.203Ki ± 0%
ComponentLifecycle-4                   2.099Mi ± 0%
SourceValidation-4                     1.984Ki ± 0%
RegistryConcurrent-4                   1.133Ki ± 0%
LoaderLoadFromString-4                 2.099Mi ± 0%
geomean                                15.05Ki

                            │ benchmark-results.txt │
                            │       allocs/op       │
InterpreterCreation-4                   15.09k ± 0%
ComponentLoad-4                         17.43k ± 0%
ComponentExecute-4                       25.00 ± 0%
PoolContention/workers-1-4               25.00 ± 0%
PoolContention/workers-2-4               25.00 ± 0%
PoolContention/workers-4-4               25.00 ± 0%
PoolContention/workers-8-4               25.00 ± 0%
PoolContention/workers-16-4              25.00 ± 0%
ComponentLifecycle-4                    17.48k ± 0%
SourceValidation-4                       32.00 ± 0%
RegistryConcurrent-4                     2.000 ± 0%
LoaderLoadFromString-4                  17.47k ± 0%
geomean                                  181.2

pkg: github.com/GoCodeAlone/workflow/middleware
cpu: AMD EPYC 7763 64-Core Processor                
                                  │ baseline-bench.txt │
                                  │       sec/op       │
CircuitBreakerDetection-4                  286.1n ± 4%
CircuitBreakerExecution_Success-4          22.54n ± 1%
CircuitBreakerExecution_Failure-4          65.33n ± 0%
geomean                                    74.96n

                                  │ baseline-bench.txt │
                                  │        B/op        │
CircuitBreakerDetection-4                 144.0 ± 0%
CircuitBreakerExecution_Success-4         0.000 ± 0%
CircuitBreakerExecution_Failure-4         0.000 ± 0%
geomean                                              ¹
¹ summaries must be >0 to compute geomean

                                  │ baseline-bench.txt │
                                  │     allocs/op      │
CircuitBreakerDetection-4                 1.000 ± 0%
CircuitBreakerExecution_Success-4         0.000 ± 0%
CircuitBreakerExecution_Failure-4         0.000 ± 0%
geomean                                              ¹
¹ summaries must be >0 to compute geomean

cpu: AMD EPYC 9V74 80-Core Processor                
                                  │ benchmark-results.txt │
                                  │        sec/op         │
CircuitBreakerDetection-4                     299.0n ± 9%
CircuitBreakerExecution_Success-4             22.69n ± 2%
CircuitBreakerExecution_Failure-4             70.42n ± 1%
geomean                                       78.17n

                                  │ benchmark-results.txt │
                                  │         B/op          │
CircuitBreakerDetection-4                    144.0 ± 0%
CircuitBreakerExecution_Success-4            0.000 ± 0%
CircuitBreakerExecution_Failure-4            0.000 ± 0%
geomean                                                 ¹
¹ summaries must be >0 to compute geomean

                                  │ benchmark-results.txt │
                                  │       allocs/op       │
CircuitBreakerDetection-4                    1.000 ± 0%
CircuitBreakerExecution_Success-4            0.000 ± 0%
CircuitBreakerExecution_Failure-4            0.000 ± 0%
geomean                                                 ¹
¹ summaries must be >0 to compute geomean

pkg: github.com/GoCodeAlone/workflow/module
cpu: AMD EPYC 7763 64-Core Processor                
                                 │ baseline-bench.txt │
                                 │       sec/op       │
JQTransform_Simple-4                     906.3n ± 30%
JQTransform_ObjectConstruction-4         1.473µ ±  1%
JQTransform_ArraySelect-4                3.411µ ±  1%
JQTransform_Complex-4                    39.12µ ±  1%
JQTransform_Throughput-4                 1.817µ ±  1%
SSEPublishDelivery-4                     66.45n ±  1%
geomean                                  1.668µ

                                 │ baseline-bench.txt │
                                 │        B/op        │
JQTransform_Simple-4                   1.273Ki ± 0%
JQTransform_ObjectConstruction-4       1.773Ki ± 0%
JQTransform_ArraySelect-4              2.625Ki ± 0%
JQTransform_Complex-4                  16.22Ki ± 0%
JQTransform_Throughput-4               1.984Ki ± 0%
SSEPublishDelivery-4                     0.000 ± 0%
geomean                                             ¹
¹ summaries must be >0 to compute geomean

                                 │ baseline-bench.txt │
                                 │     allocs/op      │
JQTransform_Simple-4                     10.00 ± 0%
JQTransform_ObjectConstruction-4         15.00 ± 0%
JQTransform_ArraySelect-4                30.00 ± 0%
JQTransform_Complex-4                    324.0 ± 0%
JQTransform_Throughput-4                 17.00 ± 0%
SSEPublishDelivery-4                     0.000 ± 0%
geomean                                             ¹
¹ summaries must be >0 to compute geomean

cpu: AMD EPYC 9V74 80-Core Processor                
                                 │ benchmark-results.txt │
                                 │        sec/op         │
JQTransform_Simple-4                        833.2n ± 32%
JQTransform_ObjectConstruction-4            1.409µ ±  1%
JQTransform_ArraySelect-4                   3.363µ ±  1%
JQTransform_Complex-4                       40.33µ ±  2%
JQTransform_Throughput-4                    1.732µ ±  1%
SSEPublishDelivery-4                        57.23n ±  1%
geomean                                     1.584µ

                                 │ benchmark-results.txt │
                                 │         B/op          │
JQTransform_Simple-4                      1.273Ki ± 0%
JQTransform_ObjectConstruction-4          1.773Ki ± 0%
JQTransform_ArraySelect-4                 2.625Ki ± 0%
JQTransform_Complex-4                     16.22Ki ± 0%
JQTransform_Throughput-4                  1.984Ki ± 0%
SSEPublishDelivery-4                        0.000 ± 0%
geomean                                                ¹
¹ summaries must be >0 to compute geomean

                                 │ benchmark-results.txt │
                                 │       allocs/op       │
JQTransform_Simple-4                        10.00 ± 0%
JQTransform_ObjectConstruction-4            15.00 ± 0%
JQTransform_ArraySelect-4                   30.00 ± 0%
JQTransform_Complex-4                       324.0 ± 0%
JQTransform_Throughput-4                    17.00 ± 0%
SSEPublishDelivery-4                        0.000 ± 0%
geomean                                                ¹
¹ summaries must be >0 to compute geomean

pkg: github.com/GoCodeAlone/workflow/schema
cpu: AMD EPYC 7763 64-Core Processor                
                                    │ baseline-bench.txt │
                                    │       sec/op       │
SchemaValidation_Simple-4                    1.113µ ± 3%
SchemaValidation_AllFields-4                 1.695µ ± 1%
SchemaValidation_FormatValidation-4          1.614µ ± 2%
SchemaValidation_ManySchemas-4               1.811µ ± 4%
geomean                                      1.532µ

                                    │ baseline-bench.txt │
                                    │        B/op        │
SchemaValidation_Simple-4                   0.000 ± 0%
SchemaValidation_AllFields-4                0.000 ± 0%
SchemaValidation_FormatValidation-4         0.000 ± 0%
SchemaValidation_ManySchemas-4              0.000 ± 0%
geomean                                                ¹
¹ summaries must be >0 to compute geomean

                                    │ baseline-bench.txt │
                                    │     allocs/op      │
SchemaValidation_Simple-4                   0.000 ± 0%
SchemaValidation_AllFields-4                0.000 ± 0%
SchemaValidation_FormatValidation-4         0.000 ± 0%
SchemaValidation_ManySchemas-4              0.000 ± 0%
geomean                                                ¹
¹ summaries must be >0 to compute geomean

cpu: AMD EPYC 9V74 80-Core Processor                
                                    │ benchmark-results.txt │
                                    │        sec/op         │
SchemaValidation_Simple-4                       1.079µ ± 5%
SchemaValidation_AllFields-4                    1.628µ ± 3%
SchemaValidation_FormatValidation-4             1.579µ ± 2%
SchemaValidation_ManySchemas-4                  1.583µ ± 1%
geomean                                         1.447µ

                                    │ benchmark-results.txt │
                                    │         B/op          │
SchemaValidation_Simple-4                      0.000 ± 0%
SchemaValidation_AllFields-4                   0.000 ± 0%
SchemaValidation_FormatValidation-4            0.000 ± 0%
SchemaValidation_ManySchemas-4                 0.000 ± 0%
geomean                                                   ¹
¹ summaries must be >0 to compute geomean

                                    │ benchmark-results.txt │
                                    │       allocs/op       │
SchemaValidation_Simple-4                      0.000 ± 0%
SchemaValidation_AllFields-4                   0.000 ± 0%
SchemaValidation_FormatValidation-4            0.000 ± 0%
SchemaValidation_ManySchemas-4                 0.000 ± 0%
geomean                                                   ¹
¹ summaries must be >0 to compute geomean

pkg: github.com/GoCodeAlone/workflow/store
cpu: AMD EPYC 7763 64-Core Processor                
                                   │ baseline-bench.txt │
                                   │       sec/op       │
EventStoreAppend_InMemory-4                1.242µ ± 26%
EventStoreAppend_SQLite-4                  1.864m ±  5%
GetTimeline_InMemory/events-10-4           14.71µ ±  3%
GetTimeline_InMemory/events-50-4           72.25µ ± 14%
GetTimeline_InMemory/events-100-4          128.2µ ±  2%
GetTimeline_InMemory/events-500-4          652.5µ ±  1%
GetTimeline_InMemory/events-1000-4         1.346m ±  3%
GetTimeline_SQLite/events-10-4             113.5µ ±  2%
GetTimeline_SQLite/events-50-4             257.0µ ±  2%
GetTimeline_SQLite/events-100-4            439.2µ ±  1%
GetTimeline_SQLite/events-500-4            1.854m ±  2%
GetTimeline_SQLite/events-1000-4           3.717m ±  3%
geomean                                    232.1µ

                                   │ baseline-bench.txt │
                                   │        B/op        │
EventStoreAppend_InMemory-4                  756.5 ± 9%
EventStoreAppend_SQLite-4                  1.984Ki ± 2%
GetTimeline_InMemory/events-10-4           7.953Ki ± 0%
GetTimeline_InMemory/events-50-4           46.62Ki ± 0%
GetTimeline_InMemory/events-100-4          94.48Ki ± 0%
GetTimeline_InMemory/events-500-4          472.8Ki ± 0%
GetTimeline_InMemory/events-1000-4         944.3Ki ± 0%
GetTimeline_SQLite/events-10-4             16.74Ki ± 0%
GetTimeline_SQLite/events-50-4             87.14Ki ± 0%
GetTimeline_SQLite/events-100-4            175.4Ki ± 0%
GetTimeline_SQLite/events-500-4            846.1Ki ± 0%
GetTimeline_SQLite/events-1000-4           1.639Mi ± 0%
geomean                                    67.10Ki

                                   │ baseline-bench.txt │
                                   │     allocs/op      │
EventStoreAppend_InMemory-4                  7.000 ± 0%
EventStoreAppend_SQLite-4                    53.00 ± 0%
GetTimeline_InMemory/events-10-4             125.0 ± 0%
GetTimeline_InMemory/events-50-4             653.0 ± 0%
GetTimeline_InMemory/events-100-4           1.306k ± 0%
GetTimeline_InMemory/events-500-4           6.514k ± 0%
GetTimeline_InMemory/events-1000-4          13.02k ± 0%
GetTimeline_SQLite/events-10-4               382.0 ± 0%
GetTimeline_SQLite/events-50-4              1.852k ± 0%
GetTimeline_SQLite/events-100-4             3.681k ± 0%
GetTimeline_SQLite/events-500-4             18.54k ± 0%
GetTimeline_SQLite/events-1000-4            37.29k ± 0%
geomean                                     1.162k

cpu: AMD EPYC 9V74 80-Core Processor                
                                   │ benchmark-results.txt │
                                   │        sec/op         │
EventStoreAppend_InMemory-4                   1.230µ ± 22%
EventStoreAppend_SQLite-4                     1.101m ±  3%
GetTimeline_InMemory/events-10-4              12.66µ ±  3%
GetTimeline_InMemory/events-50-4              56.23µ ± 24%
GetTimeline_InMemory/events-100-4             112.8µ ±  1%
GetTimeline_InMemory/events-500-4             574.9µ ±  1%
GetTimeline_InMemory/events-1000-4            1.167m ±  1%
GetTimeline_SQLite/events-10-4                97.80µ ±  1%
GetTimeline_SQLite/events-50-4                236.7µ ±  1%
GetTimeline_SQLite/events-100-4               394.0µ ±  2%
GetTimeline_SQLite/events-500-4               1.693m ±  0%
GetTimeline_SQLite/events-1000-4              3.277m ±  0%
geomean                                       198.3µ

                                   │ benchmark-results.txt │
                                   │         B/op          │
EventStoreAppend_InMemory-4                     775.5 ± 7%
EventStoreAppend_SQLite-4                     1.983Ki ± 2%
GetTimeline_InMemory/events-10-4              7.953Ki ± 0%
GetTimeline_InMemory/events-50-4              46.62Ki ± 0%
GetTimeline_InMemory/events-100-4             94.48Ki ± 0%
GetTimeline_InMemory/events-500-4             472.8Ki ± 0%
GetTimeline_InMemory/events-1000-4            944.3Ki ± 0%
GetTimeline_SQLite/events-10-4                16.74Ki ± 0%
GetTimeline_SQLite/events-50-4                87.14Ki ± 0%
GetTimeline_SQLite/events-100-4               175.4Ki ± 0%
GetTimeline_SQLite/events-500-4               846.1Ki ± 0%
GetTimeline_SQLite/events-1000-4              1.639Mi ± 0%
geomean                                       67.24Ki

                                   │ benchmark-results.txt │
                                   │       allocs/op       │
EventStoreAppend_InMemory-4                     7.000 ± 0%
EventStoreAppend_SQLite-4                       53.00 ± 0%
GetTimeline_InMemory/events-10-4                125.0 ± 0%
GetTimeline_InMemory/events-50-4                653.0 ± 0%
GetTimeline_InMemory/events-100-4              1.306k ± 0%
GetTimeline_InMemory/events-500-4              6.514k ± 0%
GetTimeline_InMemory/events-1000-4             13.02k ± 0%
GetTimeline_SQLite/events-10-4                  382.0 ± 0%
GetTimeline_SQLite/events-50-4                 1.852k ± 0%
GetTimeline_SQLite/events-100-4                3.681k ± 0%
GetTimeline_SQLite/events-500-4                18.54k ± 0%
GetTimeline_SQLite/events-1000-4               37.29k ± 0%
geomean                                        1.162k

Benchmarks run with go test -bench=. -benchmem -count=6.
Regressions ≥ 20% are flagged. Results compared via benchstat.

…ix error message and docs markdown Co-authored-by: intel352 <77607+intel352@users.noreply.github.com>

Copilot · 2026-03-12T00:31:03Z

@copilot apply changes based on the comments in this thread

Build failing, lint failing, tests fai...

Addressed all review feedback in commit 6226635:

QueryContext/ExecContext: Both the returning path and the standard exec path now propagate context cancellations/timeouts.
Shared helper: Extracted scanSQLRows + formatQueryOutput into pipeline_step_db_helpers.go; both db_exec and db_query now use them, eliminating the duplication.
Error message: "exec failed" → "query failed" in the returning path.
Docs markdown: Fixed mode: single\|list → mode: single or mode: list.
go mod tidy: Ran to resolve the build/validate CI failures.

intel352 · 2026-03-12T04:13:49Z

@copilot Look at the changes that happened in main, vs our branch, and intelligently resolve the conflict while preserving intent of both sets of changes.

…NBytesOrString into scanSQLRows helper Co-authored-by: intel352 <77607+intel352@users.noreply.github.com>

Copilot · 2026-03-12T04:24:38Z

@copilot Look at the changes that happened in main, vs our branch, and intelligently resolve the conflict while preserving intent of both sets of changes.

Merged in commit 02181b4. There was a single conflict in module/pipeline_step_db_query.go:

Main (006b368) updated the inline scan loop to use parseJSONBytesOrString(b) for proper PostgreSQL json/jsonb handling.
Our branch replaced that inline loop with the shared scanSQLRows() helper + QueryContext.

Resolution: kept our shared-helper + QueryContext approach and updated scanSQLRows() in pipeline_step_db_helpers.go to call parseJSONBytesOrString(b) instead of string(b) — so both db_query and db_exec's RETURNING path now benefit from the json/jsonb fix. All other changes from main (cors, partitioned db lifecycle hooks, auth.m2m trusted keys, step.json_parse) merged cleanly.

intel352 · 2026-03-12T10:10:08Z

@copilot Address the build, lint, test, config validation failures

…tion in pipeline_step_db_query.go Co-authored-by: intel352 <77607+intel352@users.noreply.github.com>

Copilot · 2026-03-12T10:16:03Z

@copilot Address the build, lint, test, config validation failures

Fixed in commit c492869. The previous conflict resolution left 49 lines of main's inline scan loop (lines 181–229) in pipeline_step_db_query.go after our scanSQLRows() call, causing redeclaration errors and a type mismatch on the return. Removed the dead code — build, lint, tests, and wfctl validate all pass clean now.

intel352 · 2026-03-12T10:34:18Z

@copilot Address the incoming conflict. The documentation section that is conflicted added a new column to it's table and the docs have been reordered. accept the incoming format and make sure any additions you're introducing are intelligently reflected.

…in format, add returning clause to step.db_exec entry Co-authored-by: intel352 <77607+intel352@users.noreply.github.com>

Copilot · 2026-03-12T10:43:17Z

@copilot Address the incoming conflict. The documentation section that is conflicted added a new column to it's table and the docs have been reordered. accept the incoming format and...

Resolved in commit a8770f2. Accepted main's format (3-column table with Plugin column) for the Pipeline Steps section, and updated the step.db_exec entry to include the returning clause documentation in the new format:

| `step.db_exec` | Executes parameterized SQL INSERT/UPDATE/DELETE against a named database. Supports `returning: true` with `mode: single` or `mode: list` to capture rows from a `RETURNING` clause | pipelinesteps |

All the additional steps and sections added in main (CI/CD, Platform, etc.) are preserved.

Initial plan

026c2fe

Copilot AI assigned Copilot and intel352 Mar 11, 2026

Copilot started work on behalf of intel352 March 11, 2026 23:07 View session

feat: step.db_exec supports RETURNING clause via returning:true confi…

ab3e75f

…g option Co-authored-by: intel352 <77607+intel352@users.noreply.github.com>

Copilot AI changed the title ~~[WIP] Add support for RETURNING clause in step.db_exec~~ step.db_exec: add returning mode to capture rows from RETURNING clause Mar 11, 2026

Copilot finished work on behalf of intel352 March 11, 2026 23:23

intel352 marked this pull request as ready for review March 12, 2026 00:02

Copilot AI review requested due to automatic review settings March 12, 2026 00:02

Copilot started reviewing on behalf of intel352 March 12, 2026 00:02 View session

Copilot AI reviewed Mar 12, 2026

View reviewed changes

module/pipeline_step_db_exec.go Outdated Show resolved Hide resolved

module/pipeline_step_db_exec.go Outdated Show resolved Hide resolved

DOCUMENTATION.md Outdated Show resolved Hide resolved

module/pipeline_step_db_exec.go Outdated Show resolved Hide resolved

Merge branch 'main' into copilot/support-returning-clause-insert-update

2165c28

Copilot started work on behalf of intel352 March 12, 2026 00:11 View session

refactor: use QueryContext/ExecContext, extract scanSQLRows helper, f…

6226635

…ix error message and docs markdown Co-authored-by: intel352 <77607+intel352@users.noreply.github.com>

Copilot finished work on behalf of intel352 March 12, 2026 00:31

intel352 added 2 commits March 11, 2026 23:12

Merge branch 'main' into copilot/support-returning-clause-insert-update

c1afc4a

Merge branch 'main' into copilot/support-returning-clause-insert-update

79bc493

Copilot started work on behalf of intel352 March 12, 2026 04:13 View session

merge: resolve pipeline_step_db_query.go conflict; integrate parseJSO…

02181b4

…NBytesOrString into scanSQLRows helper Co-authored-by: intel352 <77607+intel352@users.noreply.github.com>

Copilot finished work on behalf of intel352 March 12, 2026 04:25

Merge branch 'main' into copilot/support-returning-clause-insert-update

0e12f9b

Copilot started work on behalf of intel352 March 12, 2026 10:10 View session

fix: remove leftover inline scan loop from incomplete conflict resolu…

c492869

…tion in pipeline_step_db_query.go Co-authored-by: intel352 <77607+intel352@users.noreply.github.com>

Copilot finished work on behalf of intel352 March 12, 2026 10:16

Copilot started work on behalf of intel352 March 12, 2026 10:34 View session

merge: resolve DOCUMENTATION.md conflict; accept main's 3-column Plug…

a8770f2

…in format, add returning clause to step.db_exec entry Co-authored-by: intel352 <77607+intel352@users.noreply.github.com>

Copilot finished work on behalf of intel352 March 12, 2026 10:44

Merge branch 'main' into copilot/support-returning-clause-insert-update

7ae55f3

intel352 merged commit 53ec135 into main Mar 12, 2026
11 checks passed

intel352 deleted the copilot/support-returning-clause-insert-update branch March 12, 2026 10:54

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

step.db_exec: add `returning` mode to capture rows from RETURNING clause#300

step.db_exec: add `returning` mode to capture rows from RETURNING clause#300
intel352 merged 11 commits intomainfrom
copilot/support-returning-clause-insert-update

Copilot AI commented Mar 11, 2026 •

edited

Loading

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

intel352 commented Mar 12, 2026

Uh oh!

github-actions bot commented Mar 12, 2026 •

edited

Loading

Uh oh!

Copilot AI commented Mar 12, 2026

Uh oh!

intel352 commented Mar 12, 2026

Uh oh!

Copilot AI commented Mar 12, 2026

Uh oh!

intel352 commented Mar 12, 2026

Uh oh!

Copilot AI commented Mar 12, 2026

Uh oh!

intel352 commented Mar 12, 2026

Uh oh!

Copilot AI commented Mar 12, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

Copilot AI commented Mar 11, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Changes

Usage

Use Case

Proposed Solution

Option A: step.db_exec gains a returning mode

Option B: Officially document step.db_query for writes

Current Workaround

Comments on the Issue (you are @copilot in this section)

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

intel352 commented Mar 12, 2026

Uh oh!

github-actions bot commented Mar 12, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

⏱ Benchmark Results

Uh oh!

Copilot AI commented Mar 12, 2026

Uh oh!

intel352 commented Mar 12, 2026

Uh oh!

Copilot AI commented Mar 12, 2026

Uh oh!

intel352 commented Mar 12, 2026

Uh oh!

Copilot AI commented Mar 12, 2026

Uh oh!

intel352 commented Mar 12, 2026

Uh oh!

Copilot AI commented Mar 12, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Copilot AI commented Mar 11, 2026 •

edited

Loading

Option A: `step.db_exec` gains a `returning` mode

Option B: Officially document `step.db_query` for writes

github-actions bot commented Mar 12, 2026 •

edited

Loading