Define 9 new commands under `temporal activity` for standalone
(top-level) Activity Executions: start, execute, describe, list,
count, cancel, terminate, delete, result. Each mirrors the
corresponding `temporal workflow` command pattern.

Modify `complete` and `fail` to make --workflow-id optional so they
work for both workflow-scoped and standalone Activities.

Add two new reusable option sets: `activity-execution-reference`
(activity-id + run-id) and `activity-start` (full set of start
options including timeouts, retry policy, ID policies, search
attributes, headers, metadata, and priority).

All new commands are marked Experimental. Existing workflow-only
commands (pause, unpause, reset, update-options) are unchanged.

Co-authored-by: Cursor <cursoragent@cursor.com>

- cancel: Rewrite description following Python SDK style, explaining
  that cancellation is a request delivered via heartbeat response
- complete/fail: Use activity-reference option set instead of
  inlining activity-id/run-id, fixing missing short flag and
  missing "latest run" description
- fail: Clarify detail vs reason option descriptions (detail is the
  failure details payload; reason is the failure message)
- count/list: Add example queries, improve query option descriptions,
  add visibility docs links
- delete: Add note about async deletion and running activity
  termination (from proto docs)
- execute: Use "output" instead of "printed"
- update-options/pause/unpause/reset: Add "Not supported for
  standalone Activities" sentence
- Remove resolved TODO comments

Co-authored-by: Cursor <cursoragent@cursor.com>

Phase 2: Run code generation producing command structs for all 9 new
commands and 2 new option sets (ActivityReferenceOptions,
ActivityStartOptions).

Phase 3: Implement run() methods for all new commands:
- start: calls StartActivityExecution, outputs activity ID and run ID
- execute: calls StartActivityExecution + PollActivityExecution,
  outputs the activity result
- describe: calls DescribeActivityExecution with include_input and
  include_outcome
- list: calls ListActivityExecutions with pagination, table output
- count: calls CountActivityExecutions with group support
- cancel: calls RequestCancelActivityExecution
- terminate: calls TerminateActivityExecution with default reason
- delete: calls DeleteActivityExecution
- result: calls PollActivityExecution, outputs the activity result

Shared helper buildStartActivityRequest() constructs the gRPC
request from ActivityStartOptions, handling retry policy, ID
policies, search attributes, headers, user metadata, and priority.

Shared helper printActivityOutcome() formats activity results for
both text and JSON output modes.

Also adds description-header to temporal activity docs (required by
code generator) and fixes import aliasing (common/v1 -> commonpb).

Co-authored-by: Cursor <cursoragent@cursor.com>

Verify all 11 activity subcommands appear in help output (cancel,
complete, count, delete, describe, execute, fail, list, result,
start, terminate).

Verify start command exposes expected flags (activity-id, type,
task-queue, timeouts, input).

Verify complete and fail commands expose both activity-reference
options (activity-id, run-id) and the optional workflow-id flag.

Integration tests for the new RPCs are deferred until a
standalone-activity-enabled test server is available.

Co-authored-by: Cursor <cursoragent@cursor.com>

- Use 'activity complete' as the primary example instead of experimental
  'activity start' command
- Restore original description-header text for docs
- Revert unnecessary commonpb import alias (use default 'common' since no
  conflict exists in this file)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

- Activity count/list/result: use Standalone Activity Execution wording and
  'only supported for Standalone Activity Execution'
- Activity complete/fail: restore --workflow-id YourWorkflowId in examples
- Keywords: restore 'activity execution'
- Activity count/list: Search Attributes and queries; filter/to be counted
- Workflow execute: add backslash after execute in example
- Workflow start: revert to main (Initiate, Returns Workflow- and Run-IDs)
- Workflow delete: revert to main (Remove, Executions typo); remove TODO
- Workflow result: remove TODO (output verb already used)
- Workflow count/list: example query and remove TODOs; queries. wording
- Restore trailing spaces in worker deployment and task-queue docs to avoid
  whitespace-only diff noise

Co-authored-by: Cursor <cursoragent@cursor.com>

This reverts commit 2ec455d.

- Activity complete/fail: restore --workflow-id in examples
- Activity count/list: Standalone Activity Execution wording, filter/sentences, Search Attributes and queries
- All standalone-only activity commands: summary + only supported sentence
- Restore activity execution keyword
- Workflow describe: revert summary to Show Workflow Execution info
- Workflow delete: remove TODO
- Workflow terminate: revert summary to Forcefully end a Workflow Execution
- Workflow execute: add backslash after execute in example
- Workflow count/list: remove TODO show an example query
- Workflow result: remove TODO

Co-authored-by: Cursor <cursoragent@cursor.com>

- Revert all trailing-whitespace-only changes in deployment/worker sections
- Restore trailing whitespace on workflow headers line to match main
- Apply workflow start description suggestion (mention workflow execute)
- Apply id-reuse-policy description suggestion
- Apply id-conflict-policy description suggestion
- Add visibility docs link to search-attribute description

Co-authored-by: Cursor <cursoragent@cursor.com>

Individual verb subcommands already have examples.

Co-authored-by: Cursor <cursoragent@cursor.com>

The summaries already say "Standalone", making this sentence redundant
in the descriptions.

Co-authored-by: Cursor <cursoragent@cursor.com>

Co-authored-by: Cursor <cursoragent@cursor.com>

…ityExecution)

Neither the Go nor Python SDK exposes this RPC, and the server
does not support it yet.

The examples were missing the required timeout, which is confusing since
either schedule-to-close-timeout or start-to-close-timeout must be
provided. Use different timeouts in each example to illustrate both options.

The server returns an empty non-error PollActivityExecution response
when the long-poll timeout (default 20s) expires before the activity
completes. This is the server's signal to re-issue the poll. Both
execute and result were making a single call and treating the nil
outcome as a terminal error.

Extract shared pollActivityOutcome that loops until an outcome arrives.

Verifies that pollActivityOutcome retries when the server returns an
empty PollActivityExecution response (nil outcome), rather than treating
it as a terminal error. Uses a gRPC interceptor to simulate the
long-poll timeout on the first poll, then return a result on the second.

Without the fix in 384741e, this test fails with "activity outcome not
available".

- pollActivityOutcome: use `for resp.GetOutcome() == nil` loop matching
  the SDK-Go's PollActivityResult pattern
- printActivityOutcome: use type switch on GetValue() matching SDK-Go
  style, with informative default case
- Enable standalone activities in dev server (history.enableChasm,
  activity.enableStandalone) with short long-poll timeout (2s)
- Rewrite long-poll retry test as proper integration test: activity
  sleeps 3s, exceeding the 2s long-poll timeout, forcing a retry

…mands

Workflow command tests are 100% integration tests (SharedServerSuite),
with no TestHelp_* unit tests. Conform to that precedent:

- Remove TestHelp_ActivitySubcommands, TestHelp_ActivityStartFlags,
  TestHelp_ActivityCompleteFlags, TestHelp_ActivityFailFlags
- Add integration tests: Start, Execute (success, failure, poll retry),
  Result, Describe, List, Count, Cancel, Terminate
- Add startStandaloneActivity helper for tests that need a running
  standalone activity

… count/delete wording

- Revert whitespace-only reformatting of `activity complete` description
- Apply "Output a count" for `workflow count` per review suggestion
- Apply "queries" for `workflow delete` per review suggestion

- Apply suggestion: parent description → "Perform operations on Activity Executions."
- Replace "Temporal Markdown" with "standard Markdown excluding images, HTML, and script tags"

The test was asserting map[foo:bar] which is Go's internal format.
The expected output is JSON: {"foo":"bar"}.

printActivityOutcome now JSON-marshals values so complex types
(maps, slices) render as JSON rather than Go's fmt representation.

Tests verify that `activity complete` and `activity fail` work
for standalone activities (without --workflow-id, using --run-id).

Replace hand-rolled PollActivityExecution long poll loop with the SDK's
client.GetActivityHandle().Get(), which provides proper gRPC long-poll
handling and retry semantics. This is analogous to how workflow update
uses UpdateWorkflow() + updateHandle.Get().

mapToSearchAttributes sends all string values as Keyword, even when the
server schema defines the attribute as Datetime. This causes the value to
be silently stored with the wrong type, making it invisible to visibility
queries. The Int case (Float64 vs Int64) is handled by server coercion.

The SQLite dev server has a format mismatch between the STRFTIME generated
column and the Go query converter for whole-second datetime values. Keep the
test body so it can be unskipped once the server bug is fixed.

Analogous to SDK test "Polling does not cease prematurely". Activity
sleeps 12s (past the 10s gRPC defaultRPCTimeout), server returns empty
poll responses every 2s, CLI must keep retrying without timing out.

Match the SDK's pollActivityTimeout: each PollActivityExecution call
gets a fresh 60s context, preventing indefinite hangs on unresponsive
servers. If the per-request context expires but the parent context is
still alive, retry. Real server errors (e.g. NotFound) propagate
immediately.

…terface{}

In execute, if printing the "Running execution:" header fails, log the
error and continue to poll for the result rather than aborting. The
activity has already started successfully; the user should still get
their result.

Replace interface{} with any throughout the file for modern Go style.

Start the activity with explicit timeouts and retry policy flags, then
verify they round-trip through describe in both text and JSON modes.

Describe test now starts with all available non-default options
(schedule-to-close, schedule-to-start, heartbeat timeouts, full retry
policy) and verifies them in both text and JSON output.

List test now starts 3 activities and verifies --limit 2 caps output
to exactly 2 rows.

Consistent with the command description and output message which
correctly frame this as requesting cancellation rather than cancelling.

The 12s sleep test is not meaningfully distinct from
RetriesOnEmptyPollResponse (3s). Both verify the same poll retry
mechanism; the gRPC default timeout is irrelevant since we set
per-RPC context timeouts.

… tests

- Extract countGroup interface + printCountGroupsText/stripCountGroupMetadataType
  helpers to share identical group-count logic between workflow and activity count.
- Add TestStandaloneActivity_SearchAttributes: sets Keyword search attribute,
  verifies via list query and describe JSON.
- Add TestStandaloneActivity_List_Pagination: uses --page-size 2 with 5 activities
  to force multi-page pagination, verifies --limit works across page boundaries.
- Keep datetime search attribute test as separate skipped test with explanation.

Matches workflow list test pattern: verify JSON output contains
activity ID and status fields.

Assert activityId and result value in JSON output, not just status.

The command is 'temporal activity', so test names should use Activity
not StandaloneActivity. Also rename startStandaloneActivity helper
to startActivity. Complete/Fail tests that use --run-id get _ByRunId
suffix to avoid collision with pre-existing tests that use --workflow-id.

Add runId assertions to execute JSON tests. Add comments to tests
explaining why they lack JSON or text variants.

activityStatusShorthand and pendingActivityStateShorthand are only
called from printActivityDescription; define them as closures within
that function.

Make it clear the commands produce no output in any mode, not just JSON.

Combine TestActivity_Execute_Failure and _Failure_JSON into one test
with // Text and // JSON sections, matching the workflow test pattern.
Remove comment on RetriesOnEmptyPollResponse.

Remove verbose inline comments, simplify section headers to // Text,
// JSON, // Raw. Clarify cancel/terminate JSON behavior.

Describe the symptom without diagnosing the external root cause.

Reference the SQLite STRFTIME vs Go query converter format mismatch
and point to the investigation doc.