Test Ad Creative

Paste this into an assistant that can read the web, such as Claude, ChatGPT or Cursor. It reads the specification and the current LangGraph documentation, then writes two files: the graph, and a note on what did not survive the translation. Read the note first. What a runtime cannot express is the part worth arguing about, and this process is a draft to argue with.

Convert the business process below into a runnable LangGraph graph:
one Python file with a TypedDict state, a StateGraph, nodes, edges,
conditional edges and a checkpointer.

The document is a reference process written to the Agent Processes
specification. Read the specification before you start, because it defines
terms that look ordinary and are not:

  https://agentcatalog.com/spec/agent-processes

Sections 6 (the phase graph), 6.5.1 (exception edges), 6.7.1 (deviations),
7 (automation) and 8 (handoffs) are the ones this conversion turns on.

Then read the current documentation for the primitives you will need, rather
than relying on what you remember of the API:

  https://docs.langchain.com/oss/python/langgraph/interrupts
    interrupt() and Command(resume=), which is how a gate stops a run
  https://reference.langchain.com/python/langgraph/graph/state/StateGraph
    StateGraph, add_edge, add_conditional_edges, defer

WHAT THE DOCUMENT ASKS FOR

These hold wherever the process lands, and they matter more than style.

1. Each phase under `phases:` becomes one step, and keeps its name.

2. `after:` gives the edges. `after: a + b` is a join and waits for BOTH.
   Reading it as "either" is the defect the specification calls out by name.

3. Every handoff carries a key in square brackets. Each key becomes one field
   on the run's state, named exactly as the key with hyphens turned into
   underscores, and the sentence beside it becomes that field's comment. The key
   is the stable name; the sentence is prose that may be rewritten.

4. A phase MUST NOT begin before its inbound handoff exists. Where that is
   checkable, check it in the step rather than assuming it.

5. `automation: never` is a gate a person signs. The run stops there and does
   not continue until a person's decision comes back. Do not turn one into a
   notification, a log line, or an automatic transition, whatever the queue
   looks like.

6. Each line under `deviations:` is a backward or sideways edge, returning to
   the phase named on the right. The key in brackets names it, and that name
   belongs in the code.

7. A phase whose `after:` reads like "X or Y, whichever could not finish" is an
   exception edge: it is entered when those phases FAIL, not when they succeed.
   Do not wire it as an ordinary successor.

8. Anything in angle brackets is a blank the adopting organization fills in.
   Leave each one as a named constant at the top of the file with a TODO. Do not
   invent a value, a threshold or a date.

9. Record the document's `from:` line at the top of the file, so it says which
   reference process and which version it was generated from.

10. Run-scoped lines under `run-scoped:` are work that runs alongside the whole
    process rather than at one point in it, and a run may not close while one is
    unfinished. Say in the code what you did about them, including if the answer
    is that the runtime has nowhere to put them.

HOW THAT LOOKS IN LANGGRAPH

11. A phase is a node added with `add_node`, under the phase's own name.

12. The state is a TypedDict. Each handoff key is one field on it.

13. A join is the trap. `add_edge(["a", "b"], "c")` looks right and releases
    once: when a backward edge re-enters ONE arm, the joined node never runs
    again, and the run ends early reporting success rather than raising. Mark the
    joined node `defer=True` and re-check inside it that both inbound handoffs
    exist.

14. A gate is `interrupt()` inside the node, resumed with `Command(resume=...)`.
    The platform lets anything at all call resume, so require the resumed value to
    name a person and a date and refuse anything else. Say in the fidelity note
    that this proves only that whoever resumed typed a name, because
    `Command(resume=True)` from a scheduled job is indistinguishable from a person
    signing.

15. A deviation is `add_conditional_edges` with a routing function named after
    the key in brackets.

16. Pass a durable checkpointer rather than taking the in-memory default. The
    gates wait days, and the default loses every paused run on restart.

17. Leave every phase body unimplemented, raising until somebody registers an
    implementation. The automation level is a blank, so writing a body would
    answer on the adopter's behalf whether an agent may do that work.

Produce a second file alongside it, `FIDELITY.md`, and treat it as the more
important of the two. The code is for whoever builds this. The fidelity note
is for whoever has to decide whether this platform suits the process at all,
and that is usually a different person who will never read the code.

It has three parts.

**What came across.** Briefly: how many phases became steps, how many handoff
keys became state fields, which gates stop the run, which deviations became
edges. Counts and names, not reassurance.

**What did not, and what was done instead.** One entry per gap. For each one,
say what the document requires, what the platform can actually express, what
you did in its place, and what breaks if somebody later removes your
workaround. This last part matters most: a workaround nobody understands is a
workaround somebody deletes.

**What a person still has to decide.** The blanks are not a translation
failure, they are the point of a reference process, so list what has to be
filled in before this could run against anything real, and say which of those
choices the platform constrains.

Write it in plain English for somebody who has not read the specification, and
do not soften it. A translation of a reference process is a draft to argue
with, not a build artifact, and the honest account of what was lost is the most
useful thing you will produce.

Here is the process document.

```
PROCESS: test ad creative              id: <team>/test-ad-creative   v1
from: ref/mkt/test-ad-creative v1
owner: <who>                          effective: <date>
trigger: a performance question is raised against creative that is
         already running in <your paid channels>
         watch: record=<running creative> system=<your paid channels>
                change=<a performance question is raised against
                creative that is already running>
concurrency: runs may overlap - <how many> live at once, and
             <how many> against one audience
goal: one element of the running creative tested against variants of
      it, and a winner, a no difference, or an unfinished test recorded
      against the evidence bar that was written before launch
phases:
  take-in-question  - human: write down the performance question and
                      what a clear answer would change
                      owner: campaign-manager    after: trigger
                      automation: <level>
  read-current      - runs collect-and-report: what the running creative
                      delivers now, placement by placement, and how much
                      it varies from week to week
                      owner: analytics           after: take-in-question
                      by: <days>                 automation: <level>
  name-the-change   - convenes decide-and-announce: the one element the
                      test changes and what it is meant to improve
                      owner: campaign-manager    after: read-current
                      by: <days>                 automation: <level>
  design-comparison - human: how many variants, how the traffic splits
                      between them, and which placements carry the test
                      owner: media-buyer         after: name-the-change
                      by: <days>                 automation: <level>
  set-evidence-bar  - human: the minimum exposure per variant, the
                      minimum length of the run, the size of difference
                      that counts, and the conversion it is read from
                      owner: analytics
                      after: design-comparison
                      by: <days>                 automation: <level>
  commit-budget     - human: what buying that much exposure costs, and
                      whether the answer is worth the money. <who>
                      commits it
                      owner: campaign-manager    after: set-evidence-bar
                      automation: <level>
  brief-makers      - convenes briefing: every maker hears the same
                      description of the one element under test and what
                      has to stay identical to the running creative
                      owner: creative-producer   after: commit-budget
                      automation: <level>
  produce-variants  - runs build-by-talent: each variant made and sized
                      for every placement the test covers
                      owner: creative-producer   after: brief-makers
                      by: <days>                 automation: <level>
  check-variant-set - runs assessment: each variant read against the
                      test design, to find any variant that differs from
                      the running creative in more than one element
                      owner: buy-check           after: produce-variants
                      by: <days>                 automation: <level>
  get-sign-offs     - convenes approval: brand, disclosure and legal
                      sign, as named signers, against a version of every
                      variant in the set
                      owner: <your legal role>
                      after: check-variant-set
                      by: <days>                 automation: never
  wire-measurement  - human: one conversion, defined once, and a tag on
                      each variant that keeps its results separate for
                      the whole run
                      owner: conversion-tracker  after: commit-budget
                      by: launch                 automation: <level>
  check-before-on   - runs assessment: the configured test read against
                      the design, covering the split, the placements,
                      the variants loaded and the tag on each of them
                      owner: buy-check
                      after: get-sign-offs + wire-measurement
                      by: launch                 automation: <level>
  launch-test       - human: the buyer turns the variants on at the
                      agreed split, and the run records the date and
                      hour the exposure count starts from
                      owner: media-buyer         after: check-before-on
                      automation: <level>
  watch-delivery    - runs assessment: what each variant was actually
                      served, read against the split the design set
                      owner: buy-check           after: launch-test
                      every: <cadence>           automation: <level>
  read-the-result   - runs collect-and-report: exposure per variant, the
                      length of the run so far, and each variant's
                      conversion rate with its source beside it
                      owner: analytics           after: watch-delivery
                      every: <cadence>           automation: <level>
  call-the-winner   - convenes decide-and-announce: the numbers read
                      against the bar, ending in a winner, a recorded no
                      difference, or a decision to keep running
                      owner: campaign-manager    after: read-the-result
                      automation: <level>
  roll-out-winner   - human: the winning variant replaces the running
                      creative in every placement the test covered, and
                      the losing variants come off
                      owner: media-buyer         after: call-the-winner
                      by: <days>                 automation: <level>
  record-learnings  - convenes debrief: what was changed, what it cost,
                      what the test settled, and what to test next
                      owner: campaign-manager    after: roll-out-winner
                      automation: <level>
run-scoped:
  spend    - runs allocate-and-reconcile       owner: media-buyer
             cap: <n>/day
             from: launch-test   until: run close
  delivery - runs collect-and-report           owner: analytics
             every: <cadence>
             from: launch-test   until: run close
handoffs:
  take-in-question -> read-current [performance-question]: the
    question, written so that a number can answer it
  read-current -> name-the-change [current-performance]: what the
    running creative delivers now and how much it moves week to week,
    which is the figure the gap in the bar is set against
  name-the-change -> design-comparison [element-under-test]: the one
    element under test and what it is meant to improve
  design-comparison -> set-evidence-bar [comparison-design]: the number
    of variants, the split and the placements, because how much
    exposure the test needs depends on all three
  set-evidence-bar -> commit-budget [evidence-bar]: the minimum
    exposure, the minimum run length, the size of the gap and the
    conversion, at a version
  commit-budget -> brief-makers / wire-measurement [committed-test]:
    the same committed test. Both branches read one record
  brief-makers -> produce-variants [variant-brief]: the element that
    changes, and everything that has to stay identical to the running
    creative
  produce-variants -> check-variant-set [variant-set]: every variant at
    a version, beside the running creative it is being compared with
  check-variant-set -> get-sign-offs [variant-scores]: the scored set,
    with the design line behind every failure
  get-sign-offs -> check-before-on [approved-variants]: the approved
    variants at the signed version. A variant changed afterward voids
    the approval and sign-offs run again
  wire-measurement -> check-before-on [measurement-setup]: the
    conversion definition and the tag each variant carries
  check-before-on -> launch-test [checked-configuration]: the scored
    configuration, with the design line or the rule behind every
    failure
  launch-test -> watch-delivery [switch-on-record]: the date and hour
    the count starts from, and the split as configured
  watch-delivery -> read-the-result [served-split]: what each variant
    was served, so the result is read only over the period the split
    actually held
  read-the-result -> call-the-winner [result-reading]: exposure per
    variant, run length and conversion rate, each line attributed to
    its source
  call-the-winner -> roll-out-winner [winning-variant]: the winning
    variant at its signed version, and the placements it replaces the
    running creative in
  call-the-winner -> record-learnings [the-call-and-the-bar]: the call,
    its date, and the four parts of the bar with what each one stood at
    when the call was made
deviations:
  check-variant-set -> produce-variants [more-than-one-difference]: a
    variant differs from the running creative in more than the element
    under test, so it is made again
  get-sign-offs -> produce-variants [sign-off-changes]: a signer asks
    for changes, so the variants they named are made again and go back
    through the check on the set
  check-before-on -> wire-measurement [wrong-tag]: a variant carries
    the wrong tag, so the measurement is wired again before anything
    switches on
  check-before-on -> produce-variants [variant-rejected]: a platform
    rejects a variant on policy, so it is rewritten or that arm of the
    test is dropped
  watch-delivery -> launch-test [split-does-not-hold]: the platform
    stopped serving the variants at the agreed split, so the buyer
    resets it and the exposure count starts again from the moment the
    split holds
  call-the-winner -> watch-delivery [bar-not-met-yet]: not every part
    of the bar has been met, so the test keeps running and the numbers
    are read again
  call-the-winner -> record-learnings [no-variant-won]: the bar is met
    and no variant beat the running creative, so the run records a no
    difference and passes over the roll-out, leaving the running
    creative in every placement it already had
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for the budget, brand and legal
           agents>
  systems: ad platforms (write, cap: <n>/day),
           analytics (write: the conversion definition and the variant
           tags; read: reporting),
           the asset store (write),
           the media plan record (read),
           the placement and delivery record (read),
           the test record (write)
  data:    brand guidelines <version>, <your claims register>,
           the disclosure rules for <each market the ads run in>
           <version>, the running creative and what it delivers now,
           the test design and the evidence bar at their versions
policy:
  the evidence bar is written down before any money is spent, and no
    agent changes it once the test is live
  a variant that differs from the running creative in more than the
    element under test never launches
  sign-off is a human gate and is never delegated to an agent
  a variant changed after sign-off goes back through sign-offs
  the conversion the result is read from is never redefined while the
    test is running
  a winner is called only when all four parts of the bar have been met
  no more than <how many> tests run against one audience at once
  a test that runs out of budget before the bar is met is recorded as
    unfinished, and its numbers are never reported as a result
measures:
  cycle time: <target> from the question to the winner being live
  exposure: impressions per variant when the call was made, against <n>
  run length: days live when the call was made, against <n>
  decisiveness: the share of tests ending in a winner or a recorded no
                difference, against <target>
  quality gate: no winner is called before the bar is met
```

Paste this into an assistant that can read the web, such as Claude, ChatGPT or Cursor. It reads the specification and the current Agent Framework documentation, then writes two files: the workflow, and a note on what did not survive the translation. Read the note first. What a runtime cannot express is the part worth arguing about, and this process is a draft to argue with.

Convert the business process below into a runnable Microsoft Agent Framework workflow:
one Python file with Executor classes, a WorkflowBuilder, typed edges,
request_info gates and durable checkpoint storage.

The document is a reference process written to the Agent Processes
specification. Read the specification before you start, because it defines
terms that look ordinary and are not:

  https://agentcatalog.com/spec/agent-processes

Sections 6 (the phase graph), 6.5.1 (exception edges), 6.7.1 (deviations),
7 (automation) and 8 (handoffs) are the ones this conversion turns on.

Then read the current documentation for the primitives you will need, rather
than relying on what you remember of the API:

  https://learn.microsoft.com/en-us/agent-framework/workflows/human-in-the-loop
    ctx.request_info, @response_handler, and answering a parked run later
  https://learn.microsoft.com/en-us/agent-framework/workflows/checkpoints
    what a checkpoint holds, and allowed_checkpoint_types
  https://learn.microsoft.com/en-us/agent-framework/concepts/workflows/edges
    add_edge with condition, add_fan_in_edges, add_switch_case_edge_group
  https://learn.microsoft.com/en-us/agent-framework/concepts/workflows/state
    ctx.set_state and ctx.get_state as they actually are today

WHAT THE DOCUMENT ASKS FOR

These hold wherever the process lands, and they matter more than style.

1. Each phase under `phases:` becomes one step, and keeps its name.

2. `after:` gives the edges. `after: a + b` is a join and waits for BOTH.
   Reading it as "either" is the defect the specification calls out by name.

3. Every handoff carries a key in square brackets. Each key becomes one field
   on the run's state, named exactly as the key with hyphens turned into
   underscores, and the sentence beside it becomes that field's comment. The key
   is the stable name; the sentence is prose that may be rewritten.

4. A phase MUST NOT begin before its inbound handoff exists. Where that is
   checkable, check it in the step rather than assuming it.

5. `automation: never` is a gate a person signs. The run stops there and does
   not continue until a person's decision comes back. Do not turn one into a
   notification, a log line, or an automatic transition, whatever the queue
   looks like.

6. Each line under `deviations:` is a backward or sideways edge, returning to
   the phase named on the right. The key in brackets names it, and that name
   belongs in the code.

7. A phase whose `after:` reads like "X or Y, whichever could not finish" is an
   exception edge: it is entered when those phases FAIL, not when they succeed.
   Do not wire it as an ordinary successor.

8. Anything in angle brackets is a blank the adopting organization fills in.
   Leave each one as a named constant at the top of the file with a TODO. Do not
   invent a value, a threshold or a date.

9. Record the document's `from:` line at the top of the file, so it says which
   reference process and which version it was generated from.

10. Run-scoped lines under `run-scoped:` are work that runs alongside the whole
    process rather than at one point in it, and a run may not close while one is
    unfinished. Say in the code what you did about them, including if the answer
    is that the runtime has nowhere to put them.

HOW THAT LOOKS IN MICROSOFT AGENT FRAMEWORK

11. Write for Python, and read those pages before writing a line. This API has
    moved: `set_shared_state`, `RequestInfoExecutor`, `RequestInfoMessage` and
    `send_responses_streaming` are all in the training data and none of them exist
    any more. The .NET workflow API differs in kind rather than in spelling, so a
    file written for one does not port by renaming.

12. A phase is a class deriving from `Executor` whose `super().__init__(id=...)`
    takes the phase name verbatim. The id is not cosmetic: a checkpoint stores a
    signature over the topology and the executor ids, so an id built from a run, a
    timestamp or a counter cannot be resumed into.

13. Give each phase a `@handler` method and move work on with
    `await ctx.send_message(...)`. A handler that returns without sending is a dead
    end: the branch stops, the run converges, and it reports success. So a phase
    you are deliberately leaving unimplemented must still send a placeholder
    onward. Do not stub with `raise NotImplementedError`, which fails the run
    instead of leaving it runnable.

14. `after: a` is `builder.add_edge(a, b)`. `after: a + b` is
    `builder.add_fan_in_edges([a, b], target)`, and the target's handler must be
    annotated `list[T]`, because a fan-in delivers one aggregated list rather than
    the separate messages. A handler typed for the single value is dropped as a
    mismatch with nothing raised.

15. The join is the trap here, and it is the opposite of LangGraph's. The
    barrier re-arms: it clears its buffer when it fires and then demands a fresh
    message from every source. So a deviation that re-enters ONE arm parks the
    run forever waiting for an arm that will not run again, and the workflow ends
    IDLE reporting success. Wherever a deviation re-enters one arm of a join,
    replace the barrier with an ordinary edge from each arm into a small executor
    that records each arrival with `ctx.set_state` and only forwards when every
    expected key is present, and say in a comment that putting `add_fan_in_edges`
    back reintroduces the stall.

16. A phase that is both a join target and a deviation target needs two
    handlers, one annotated `list[T]` for the barrier and one annotated `T` for the
    backward message. Write only the list handler and every backward edge into it
    is discarded as a type mismatch, silently.

17. `automation: never` is `await ctx.request_info(request_data=...,
    response_type=...)` inside the phase, answered by a `@response_handler` on the
    same executor whose annotations match those exact types. The run parks at
    `IDLE_WITH_PENDING_REQUESTS` and the host answers with
    `workflow.run(stream=True, responses={request_id: value})`. If no handler
    matches the pair, the framework logs a warning and parks anyway, so the gate
    reads as working right up until somebody asks why the approval did not take.

18. A gate is only a gate if the wait survives a restart, so pass
    `checkpoint_storage=FileCheckpointStorage(...)` to the builder. Checkpointing
    is off by default and `InMemoryCheckpointStorage` reads as configured while
    persisting nothing. Register every handoff payload type in
    `allowed_checkpoint_types`, or the first restore raises. Anything an executor
    keeps as an instance attribute is absent after a restore unless you export it
    from `on_checkpoint_save` and read it back in `on_checkpoint_restore`, and it
    comes back empty rather than missing.

19. Each line under `deviations:` is `builder.add_edge(source, earlier,
    condition=fn)` with `fn` named after the key. Cycles are legal and unchecked,
    but raise `max_iterations` well above its default of 100, because several live
    cycles will exhaust a budget sized for a straight line and fail with a message
    about convergence that reads like a broken graph. Keep the ordinary forward
    edge unconditional and add each deviation beside it: a condition that returns
    false is dropped with no event, so a forward path expressed as a condition
    dies silently on every normal run, which is most of them.

20. Handoff values go in `ctx.set_state(key, value)` and come back from
    `ctx.get_state(key)`, untyped and unchecked. A write is visible to its writer
    at once and to everyone else only in the next superstep, and two writers of one
    key in a superstep keep the last write. Never read a key in the same superstep
    another phase wrote it.

21. There are no timers, no deadlines and no scheduled wakes. Nothing in
    `run-scoped:` becomes an executor and `by:` has no expression at all, so write
    them as comments naming where they start and stop, and say plainly in the
    fidelity note that a run can close over an unfinished run-scoped line. Do not
    fake a deadline with a sleep inside a handler, which blocks the whole superstep
    barrier, and never let an expiring wait release a gate.

Produce a second file alongside it, `FIDELITY.md`, and treat it as the more
important of the two. The code is for whoever builds this. The fidelity note
is for whoever has to decide whether this platform suits the process at all,
and that is usually a different person who will never read the code.

It has three parts.

**What came across.** Briefly: how many phases became steps, how many handoff
keys became state fields, which gates stop the run, which deviations became
edges. Counts and names, not reassurance.

**What did not, and what was done instead.** One entry per gap. For each one,
say what the document requires, what the platform can actually express, what
you did in its place, and what breaks if somebody later removes your
workaround. This last part matters most: a workaround nobody understands is a
workaround somebody deletes.

**What a person still has to decide.** The blanks are not a translation
failure, they are the point of a reference process, so list what has to be
filled in before this could run against anything real, and say which of those
choices the platform constrains.

Write it in plain English for somebody who has not read the specification, and
do not soften it. A translation of a reference process is a draft to argue
with, not a build artifact, and the honest account of what was lost is the most
useful thing you will produce.

Here is the process document.

```
PROCESS: test ad creative              id: <team>/test-ad-creative   v1
from: ref/mkt/test-ad-creative v1
owner: <who>                          effective: <date>
trigger: a performance question is raised against creative that is
         already running in <your paid channels>
         watch: record=<running creative> system=<your paid channels>
                change=<a performance question is raised against
                creative that is already running>
concurrency: runs may overlap - <how many> live at once, and
             <how many> against one audience
goal: one element of the running creative tested against variants of
      it, and a winner, a no difference, or an unfinished test recorded
      against the evidence bar that was written before launch
phases:
  take-in-question  - human: write down the performance question and
                      what a clear answer would change
                      owner: campaign-manager    after: trigger
                      automation: <level>
  read-current      - runs collect-and-report: what the running creative
                      delivers now, placement by placement, and how much
                      it varies from week to week
                      owner: analytics           after: take-in-question
                      by: <days>                 automation: <level>
  name-the-change   - convenes decide-and-announce: the one element the
                      test changes and what it is meant to improve
                      owner: campaign-manager    after: read-current
                      by: <days>                 automation: <level>
  design-comparison - human: how many variants, how the traffic splits
                      between them, and which placements carry the test
                      owner: media-buyer         after: name-the-change
                      by: <days>                 automation: <level>
  set-evidence-bar  - human: the minimum exposure per variant, the
                      minimum length of the run, the size of difference
                      that counts, and the conversion it is read from
                      owner: analytics
                      after: design-comparison
                      by: <days>                 automation: <level>
  commit-budget     - human: what buying that much exposure costs, and
                      whether the answer is worth the money. <who>
                      commits it
                      owner: campaign-manager    after: set-evidence-bar
                      automation: <level>
  brief-makers      - convenes briefing: every maker hears the same
                      description of the one element under test and what
                      has to stay identical to the running creative
                      owner: creative-producer   after: commit-budget
                      automation: <level>
  produce-variants  - runs build-by-talent: each variant made and sized
                      for every placement the test covers
                      owner: creative-producer   after: brief-makers
                      by: <days>                 automation: <level>
  check-variant-set - runs assessment: each variant read against the
                      test design, to find any variant that differs from
                      the running creative in more than one element
                      owner: buy-check           after: produce-variants
                      by: <days>                 automation: <level>
  get-sign-offs     - convenes approval: brand, disclosure and legal
                      sign, as named signers, against a version of every
                      variant in the set
                      owner: <your legal role>
                      after: check-variant-set
                      by: <days>                 automation: never
  wire-measurement  - human: one conversion, defined once, and a tag on
                      each variant that keeps its results separate for
                      the whole run
                      owner: conversion-tracker  after: commit-budget
                      by: launch                 automation: <level>
  check-before-on   - runs assessment: the configured test read against
                      the design, covering the split, the placements,
                      the variants loaded and the tag on each of them
                      owner: buy-check
                      after: get-sign-offs + wire-measurement
                      by: launch                 automation: <level>
  launch-test       - human: the buyer turns the variants on at the
                      agreed split, and the run records the date and
                      hour the exposure count starts from
                      owner: media-buyer         after: check-before-on
                      automation: <level>
  watch-delivery    - runs assessment: what each variant was actually
                      served, read against the split the design set
                      owner: buy-check           after: launch-test
                      every: <cadence>           automation: <level>
  read-the-result   - runs collect-and-report: exposure per variant, the
                      length of the run so far, and each variant's
                      conversion rate with its source beside it
                      owner: analytics           after: watch-delivery
                      every: <cadence>           automation: <level>
  call-the-winner   - convenes decide-and-announce: the numbers read
                      against the bar, ending in a winner, a recorded no
                      difference, or a decision to keep running
                      owner: campaign-manager    after: read-the-result
                      automation: <level>
  roll-out-winner   - human: the winning variant replaces the running
                      creative in every placement the test covered, and
                      the losing variants come off
                      owner: media-buyer         after: call-the-winner
                      by: <days>                 automation: <level>
  record-learnings  - convenes debrief: what was changed, what it cost,
                      what the test settled, and what to test next
                      owner: campaign-manager    after: roll-out-winner
                      automation: <level>
run-scoped:
  spend    - runs allocate-and-reconcile       owner: media-buyer
             cap: <n>/day
             from: launch-test   until: run close
  delivery - runs collect-and-report           owner: analytics
             every: <cadence>
             from: launch-test   until: run close
handoffs:
  take-in-question -> read-current [performance-question]: the
    question, written so that a number can answer it
  read-current -> name-the-change [current-performance]: what the
    running creative delivers now and how much it moves week to week,
    which is the figure the gap in the bar is set against
  name-the-change -> design-comparison [element-under-test]: the one
    element under test and what it is meant to improve
  design-comparison -> set-evidence-bar [comparison-design]: the number
    of variants, the split and the placements, because how much
    exposure the test needs depends on all three
  set-evidence-bar -> commit-budget [evidence-bar]: the minimum
    exposure, the minimum run length, the size of the gap and the
    conversion, at a version
  commit-budget -> brief-makers / wire-measurement [committed-test]:
    the same committed test. Both branches read one record
  brief-makers -> produce-variants [variant-brief]: the element that
    changes, and everything that has to stay identical to the running
    creative
  produce-variants -> check-variant-set [variant-set]: every variant at
    a version, beside the running creative it is being compared with
  check-variant-set -> get-sign-offs [variant-scores]: the scored set,
    with the design line behind every failure
  get-sign-offs -> check-before-on [approved-variants]: the approved
    variants at the signed version. A variant changed afterward voids
    the approval and sign-offs run again
  wire-measurement -> check-before-on [measurement-setup]: the
    conversion definition and the tag each variant carries
  check-before-on -> launch-test [checked-configuration]: the scored
    configuration, with the design line or the rule behind every
    failure
  launch-test -> watch-delivery [switch-on-record]: the date and hour
    the count starts from, and the split as configured
  watch-delivery -> read-the-result [served-split]: what each variant
    was served, so the result is read only over the period the split
    actually held
  read-the-result -> call-the-winner [result-reading]: exposure per
    variant, run length and conversion rate, each line attributed to
    its source
  call-the-winner -> roll-out-winner [winning-variant]: the winning
    variant at its signed version, and the placements it replaces the
    running creative in
  call-the-winner -> record-learnings [the-call-and-the-bar]: the call,
    its date, and the four parts of the bar with what each one stood at
    when the call was made
deviations:
  check-variant-set -> produce-variants [more-than-one-difference]: a
    variant differs from the running creative in more than the element
    under test, so it is made again
  get-sign-offs -> produce-variants [sign-off-changes]: a signer asks
    for changes, so the variants they named are made again and go back
    through the check on the set
  check-before-on -> wire-measurement [wrong-tag]: a variant carries
    the wrong tag, so the measurement is wired again before anything
    switches on
  check-before-on -> produce-variants [variant-rejected]: a platform
    rejects a variant on policy, so it is rewritten or that arm of the
    test is dropped
  watch-delivery -> launch-test [split-does-not-hold]: the platform
    stopped serving the variants at the agreed split, so the buyer
    resets it and the exposure count starts again from the moment the
    split holds
  call-the-winner -> watch-delivery [bar-not-met-yet]: not every part
    of the bar has been met, so the test keeps running and the numbers
    are read again
  call-the-winner -> record-learnings [no-variant-won]: the bar is met
    and no variant beat the running creative, so the run records a no
    difference and passes over the roll-out, leaving the running
    creative in every placement it already had
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for the budget, brand and legal
           agents>
  systems: ad platforms (write, cap: <n>/day),
           analytics (write: the conversion definition and the variant
           tags; read: reporting),
           the asset store (write),
           the media plan record (read),
           the placement and delivery record (read),
           the test record (write)
  data:    brand guidelines <version>, <your claims register>,
           the disclosure rules for <each market the ads run in>
           <version>, the running creative and what it delivers now,
           the test design and the evidence bar at their versions
policy:
  the evidence bar is written down before any money is spent, and no
    agent changes it once the test is live
  a variant that differs from the running creative in more than the
    element under test never launches
  sign-off is a human gate and is never delegated to an agent
  a variant changed after sign-off goes back through sign-offs
  the conversion the result is read from is never redefined while the
    test is running
  a winner is called only when all four parts of the bar have been met
  no more than <how many> tests run against one audience at once
  a test that runs out of budget before the bar is met is recorded as
    unfinished, and its numbers are never reported as a result
measures:
  cycle time: <target> from the question to the winner being live
  exposure: impressions per variant when the call was made, against <n>
  run length: days live when the call was made, against <n>
  decisiveness: the share of tests ending in a winner or a recorded no
                difference, against <target>
  quality gate: no winner is called before the bar is met
```

Paste this into an assistant that can read the web, such as Claude, ChatGPT or Cursor. It reads the specification and the current CrewAI documentation, then writes two files: the flow, and a note on what did not survive the translation. Read the note first. What a runtime cannot express is the part worth arguing about, and this process is a draft to argue with.

Convert the business process below into a runnable CrewAI Flow:
one Python file with a Pydantic state model, one Flow subclass, @start,
@listen, @router and a durable human feedback provider.

The document is a reference process written to the Agent Processes
specification. Read the specification before you start, because it defines
terms that look ordinary and are not:

  https://agentcatalog.com/spec/agent-processes

Sections 6 (the phase graph), 6.5.1 (exception edges), 6.7.1 (deviations),
7 (automation) and 8 (handoffs) are the ones this conversion turns on.

Then read the current documentation for the primitives you will need, rather
than relying on what you remember of the API:

  https://docs.crewai.com/en/concepts/flows
    Flow, @start, @listen, @router, and_, or_, state, kickoff, plot
  https://docs.crewai.com/en/learn/human-feedback-in-flows
    @human_feedback, the provider protocol, from_pending and resume
  https://docs.crewai.com/en/guides/flows/mastering-flow-state
    @persist and what persistence actually promises, which is less than it sounds

WHAT THE DOCUMENT ASKS FOR

These hold wherever the process lands, and they matter more than style.

1. Each phase under `phases:` becomes one step, and keeps its name.

2. `after:` gives the edges. `after: a + b` is a join and waits for BOTH.
   Reading it as "either" is the defect the specification calls out by name.

3. Every handoff carries a key in square brackets. Each key becomes one field
   on the run's state, named exactly as the key with hyphens turned into
   underscores, and the sentence beside it becomes that field's comment. The key
   is the stable name; the sentence is prose that may be rewritten.

4. A phase MUST NOT begin before its inbound handoff exists. Where that is
   checkable, check it in the step rather than assuming it.

5. `automation: never` is a gate a person signs. The run stops there and does
   not continue until a person's decision comes back. Do not turn one into a
   notification, a log line, or an automatic transition, whatever the queue
   looks like.

6. Each line under `deviations:` is a backward or sideways edge, returning to
   the phase named on the right. The key in brackets names it, and that name
   belongs in the code.

7. A phase whose `after:` reads like "X or Y, whichever could not finish" is an
   exception edge: it is entered when those phases FAIL, not when they succeed.
   Do not wire it as an ordinary successor.

8. Anything in angle brackets is a blank the adopting organization fills in.
   Leave each one as a named constant at the top of the file with a TODO. Do not
   invent a value, a threshold or a date.

9. Record the document's `from:` line at the top of the file, so it says which
   reference process and which version it was generated from.

10. Run-scoped lines under `run-scoped:` are work that runs alongside the whole
    process rather than at one point in it, and a run may not close while one is
    unfinished. Say in the code what you did about them, including if the answer
    is that the runtime has nowhere to put them.

HOW THAT LOOKS IN CREWAI FLOWS

11. Build a Flow, not a Crew. A Crew is a team of roles with no graph, no join,
    no persistence handle and no gate, and cannot express this document at all.
    Each phase is one method on a single `Flow` subclass, keeping its name with
    hyphens turned into underscores. A phase that genuinely needs role-based agents
    builds its own Crew inside its own method body, and the Flow stays the graph.

12. Declare the state as a Pydantic model bound as the type parameter,
    `class NegotiateTheAgreement(Flow[NegotiationState])`, and read and write
    `self.state.field`. Never use the untyped dict form: the handoff keys are this
    process's memory, and an untyped dict turns a misspelt key into a handoff that
    is silently absent. Keep the auto-injected `id` field, which is what every
    resume depends on.

13. `after: a` is `@listen(a)`. `after: a + b` is `@listen(and_(a, b))`. Never
    write `or_` where the document writes `+`.

14. Check every inbound handoff at the top of the method and raise if one is
    missing. `@listen` says when a method may run and says nothing about what is
    in hand when it does.

15. The join is the trap, and it is proven rather than theoretical. `and_()`
    empties its accumulator the moment it fires, so re-entering BOTH arms works
    forever, and re-entering ONE arm after it has fired leaves it holding a single
    trigger and waiting for the other for good. The cascade drains, CrewAI prints
    that the flow completed, and `kickoff()` returns normally. So for any joining
    phase that a deviation can send work back into, do not use `and_()` at all:
    make the join a `@router` that both arms trigger, which reads the state fields
    and emits its label only when every inbound handoff is present. A router is
    re-evaluated against durable state every time and is never suppressed by the
    once-fired set.

16. Do not write a phase as `@listen(or_(and_(a, b), "some_label"))`. There is
    one accumulator per listener, shared across every branch of its condition and
    wiped when any branch satisfies, so the label firing while the join is half
    full erases the arm that had already arrived.

17. `automation: never` is `@human_feedback(message=..., provider=...)` stacked
    under the method's `@listen`, with a provider whose `request_feedback` raises
    `HumanFeedbackPending`. The run then persists, returns that object from
    `kickoff()`, and a different process answers later with `from_pending(flow_id,
    persistence)` and `resume(text)`. Do not take the default `ConsoleProvider`,
    which calls `input()`: that gate exists only while somebody is watching a
    terminal, and a run started by a scheduler either hangs or takes an empty
    string.

18. Silence must not approve, and the platform's default is that it does. With
    `emit=[...]` set, an empty resume collapses to `default_outcome`, or to the
    first label when that is unset, with no model consulted and nobody named. Treat
    an empty or unrecognised answer as a refusal in your own router. And write the
    approver's name and the time onto the state yourself, because
    `HumanFeedbackResult` carries the text, the outcome and a timestamp but has no
    field for the person, which the specification requires.

19. Each line under `deviations:` is a `@router` named after the key, returning
    a label named after the same key, with the target subscribing as
    `@listen(or_(normal_trigger, "the_label"))`. Route rather than listen
    directly, because a router is re-evaluated on every cycle while a top-level
    `or_` listener is suppressed after it first fires.

20. An exception edge is a `try` and `except` around the failing phase's body,
    recording the failure on the state and emitting an exception label from a
    router. Wiring it as `@listen(or_(x, y))` fires when those phases SUCCEED, so
    the clearing phase would run on every healthy run.

21. An unimplemented phase is a method with the document's own sentence as its
    docstring and a bare `pass`, which is safe because listeners still fire on a
    `None` return. An unimplemented `@router` is not safe: returning `None` emits
    no label, every phase below it disappears from the run including the gates, and
    the flow reports success. A stub router must return a hard-coded label with a
    TODO beside it, or raise.

22. Turn persistence on with `@persist(SQLiteFlowPersistence(...))`, then treat
    every phase that performs a real act as something that will run twice.
    Persistence saves the state fields and nothing else, so a restart rehydrates
    the data and runs the graph again from `@start`: a flow that had already sent a
    written refusal sends a second one. Guard each acting phase with a state field
    it checks and sets.

23. There are no timers, no deadlines and no cadences, and `run-scoped:` has no
    counterpart at all. Put each `by:` value as a named constant, name the
    run-scoped lines in the module docstring as unimplemented obligations, and say
    in the fidelity note that no deadline in this document is enforced by anything.
    These absences produce no diagnostic whatsoever, which is exactly why they have
    to be written down.

Produce a second file alongside it, `FIDELITY.md`, and treat it as the more
important of the two. The code is for whoever builds this. The fidelity note
is for whoever has to decide whether this platform suits the process at all,
and that is usually a different person who will never read the code.

It has three parts.

**What came across.** Briefly: how many phases became steps, how many handoff
keys became state fields, which gates stop the run, which deviations became
edges. Counts and names, not reassurance.

**What did not, and what was done instead.** One entry per gap. For each one,
say what the document requires, what the platform can actually express, what
you did in its place, and what breaks if somebody later removes your
workaround. This last part matters most: a workaround nobody understands is a
workaround somebody deletes.

**What a person still has to decide.** The blanks are not a translation
failure, they are the point of a reference process, so list what has to be
filled in before this could run against anything real, and say which of those
choices the platform constrains.

Write it in plain English for somebody who has not read the specification, and
do not soften it. A translation of a reference process is a draft to argue
with, not a build artifact, and the honest account of what was lost is the most
useful thing you will produce.

Here is the process document.

```
PROCESS: test ad creative              id: <team>/test-ad-creative   v1
from: ref/mkt/test-ad-creative v1
owner: <who>                          effective: <date>
trigger: a performance question is raised against creative that is
         already running in <your paid channels>
         watch: record=<running creative> system=<your paid channels>
                change=<a performance question is raised against
                creative that is already running>
concurrency: runs may overlap - <how many> live at once, and
             <how many> against one audience
goal: one element of the running creative tested against variants of
      it, and a winner, a no difference, or an unfinished test recorded
      against the evidence bar that was written before launch
phases:
  take-in-question  - human: write down the performance question and
                      what a clear answer would change
                      owner: campaign-manager    after: trigger
                      automation: <level>
  read-current      - runs collect-and-report: what the running creative
                      delivers now, placement by placement, and how much
                      it varies from week to week
                      owner: analytics           after: take-in-question
                      by: <days>                 automation: <level>
  name-the-change   - convenes decide-and-announce: the one element the
                      test changes and what it is meant to improve
                      owner: campaign-manager    after: read-current
                      by: <days>                 automation: <level>
  design-comparison - human: how many variants, how the traffic splits
                      between them, and which placements carry the test
                      owner: media-buyer         after: name-the-change
                      by: <days>                 automation: <level>
  set-evidence-bar  - human: the minimum exposure per variant, the
                      minimum length of the run, the size of difference
                      that counts, and the conversion it is read from
                      owner: analytics
                      after: design-comparison
                      by: <days>                 automation: <level>
  commit-budget     - human: what buying that much exposure costs, and
                      whether the answer is worth the money. <who>
                      commits it
                      owner: campaign-manager    after: set-evidence-bar
                      automation: <level>
  brief-makers      - convenes briefing: every maker hears the same
                      description of the one element under test and what
                      has to stay identical to the running creative
                      owner: creative-producer   after: commit-budget
                      automation: <level>
  produce-variants  - runs build-by-talent: each variant made and sized
                      for every placement the test covers
                      owner: creative-producer   after: brief-makers
                      by: <days>                 automation: <level>
  check-variant-set - runs assessment: each variant read against the
                      test design, to find any variant that differs from
                      the running creative in more than one element
                      owner: buy-check           after: produce-variants
                      by: <days>                 automation: <level>
  get-sign-offs     - convenes approval: brand, disclosure and legal
                      sign, as named signers, against a version of every
                      variant in the set
                      owner: <your legal role>
                      after: check-variant-set
                      by: <days>                 automation: never
  wire-measurement  - human: one conversion, defined once, and a tag on
                      each variant that keeps its results separate for
                      the whole run
                      owner: conversion-tracker  after: commit-budget
                      by: launch                 automation: <level>
  check-before-on   - runs assessment: the configured test read against
                      the design, covering the split, the placements,
                      the variants loaded and the tag on each of them
                      owner: buy-check
                      after: get-sign-offs + wire-measurement
                      by: launch                 automation: <level>
  launch-test       - human: the buyer turns the variants on at the
                      agreed split, and the run records the date and
                      hour the exposure count starts from
                      owner: media-buyer         after: check-before-on
                      automation: <level>
  watch-delivery    - runs assessment: what each variant was actually
                      served, read against the split the design set
                      owner: buy-check           after: launch-test
                      every: <cadence>           automation: <level>
  read-the-result   - runs collect-and-report: exposure per variant, the
                      length of the run so far, and each variant's
                      conversion rate with its source beside it
                      owner: analytics           after: watch-delivery
                      every: <cadence>           automation: <level>
  call-the-winner   - convenes decide-and-announce: the numbers read
                      against the bar, ending in a winner, a recorded no
                      difference, or a decision to keep running
                      owner: campaign-manager    after: read-the-result
                      automation: <level>
  roll-out-winner   - human: the winning variant replaces the running
                      creative in every placement the test covered, and
                      the losing variants come off
                      owner: media-buyer         after: call-the-winner
                      by: <days>                 automation: <level>
  record-learnings  - convenes debrief: what was changed, what it cost,
                      what the test settled, and what to test next
                      owner: campaign-manager    after: roll-out-winner
                      automation: <level>
run-scoped:
  spend    - runs allocate-and-reconcile       owner: media-buyer
             cap: <n>/day
             from: launch-test   until: run close
  delivery - runs collect-and-report           owner: analytics
             every: <cadence>
             from: launch-test   until: run close
handoffs:
  take-in-question -> read-current [performance-question]: the
    question, written so that a number can answer it
  read-current -> name-the-change [current-performance]: what the
    running creative delivers now and how much it moves week to week,
    which is the figure the gap in the bar is set against
  name-the-change -> design-comparison [element-under-test]: the one
    element under test and what it is meant to improve
  design-comparison -> set-evidence-bar [comparison-design]: the number
    of variants, the split and the placements, because how much
    exposure the test needs depends on all three
  set-evidence-bar -> commit-budget [evidence-bar]: the minimum
    exposure, the minimum run length, the size of the gap and the
    conversion, at a version
  commit-budget -> brief-makers / wire-measurement [committed-test]:
    the same committed test. Both branches read one record
  brief-makers -> produce-variants [variant-brief]: the element that
    changes, and everything that has to stay identical to the running
    creative
  produce-variants -> check-variant-set [variant-set]: every variant at
    a version, beside the running creative it is being compared with
  check-variant-set -> get-sign-offs [variant-scores]: the scored set,
    with the design line behind every failure
  get-sign-offs -> check-before-on [approved-variants]: the approved
    variants at the signed version. A variant changed afterward voids
    the approval and sign-offs run again
  wire-measurement -> check-before-on [measurement-setup]: the
    conversion definition and the tag each variant carries
  check-before-on -> launch-test [checked-configuration]: the scored
    configuration, with the design line or the rule behind every
    failure
  launch-test -> watch-delivery [switch-on-record]: the date and hour
    the count starts from, and the split as configured
  watch-delivery -> read-the-result [served-split]: what each variant
    was served, so the result is read only over the period the split
    actually held
  read-the-result -> call-the-winner [result-reading]: exposure per
    variant, run length and conversion rate, each line attributed to
    its source
  call-the-winner -> roll-out-winner [winning-variant]: the winning
    variant at its signed version, and the placements it replaces the
    running creative in
  call-the-winner -> record-learnings [the-call-and-the-bar]: the call,
    its date, and the four parts of the bar with what each one stood at
    when the call was made
deviations:
  check-variant-set -> produce-variants [more-than-one-difference]: a
    variant differs from the running creative in more than the element
    under test, so it is made again
  get-sign-offs -> produce-variants [sign-off-changes]: a signer asks
    for changes, so the variants they named are made again and go back
    through the check on the set
  check-before-on -> wire-measurement [wrong-tag]: a variant carries
    the wrong tag, so the measurement is wired again before anything
    switches on
  check-before-on -> produce-variants [variant-rejected]: a platform
    rejects a variant on policy, so it is rewritten or that arm of the
    test is dropped
  watch-delivery -> launch-test [split-does-not-hold]: the platform
    stopped serving the variants at the agreed split, so the buyer
    resets it and the exposure count starts again from the moment the
    split holds
  call-the-winner -> watch-delivery [bar-not-met-yet]: not every part
    of the bar has been met, so the test keeps running and the numbers
    are read again
  call-the-winner -> record-learnings [no-variant-won]: the bar is met
    and no variant beat the running creative, so the run records a no
    difference and passes over the roll-out, leaving the running
    creative in every placement it already had
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for the budget, brand and legal
           agents>
  systems: ad platforms (write, cap: <n>/day),
           analytics (write: the conversion definition and the variant
           tags; read: reporting),
           the asset store (write),
           the media plan record (read),
           the placement and delivery record (read),
           the test record (write)
  data:    brand guidelines <version>, <your claims register>,
           the disclosure rules for <each market the ads run in>
           <version>, the running creative and what it delivers now,
           the test design and the evidence bar at their versions
policy:
  the evidence bar is written down before any money is spent, and no
    agent changes it once the test is live
  a variant that differs from the running creative in more than the
    element under test never launches
  sign-off is a human gate and is never delegated to an agent
  a variant changed after sign-off goes back through sign-offs
  the conversion the result is read from is never redefined while the
    test is running
  a winner is called only when all four parts of the bar have been met
  no more than <how many> tests run against one audience at once
  a test that runs out of budget before the bar is met is recorded as
    unfinished, and its numbers are never reported as a result
measures:
  cycle time: <target> from the question to the winner being live
  exposure: impressions per variant when the call was made, against <n>
  run length: days live when the call was made, against <n>
  decisiveness: the share of tests ending in a winner or a recorded no
                difference, against <target>
  quality gate: no winner is called before the bar is met
```

Paste this into an assistant that can read the web, such as Claude, ChatGPT or Cursor. It reads the specification and the current ADK documentation, then writes two files: the workflow, and a note on what did not survive the translation. Read the note first. What a runtime cannot express is the part worth arguing about, and this process is a draft to argue with.

Convert the business process below into a runnable Google ADK workflow:
one Python file with a Workflow, nodes, routed edges, a JoinNode,
RequestInput gates and a persisting session service.

The document is a reference process written to the Agent Processes
specification. Read the specification before you start, because it defines
terms that look ordinary and are not:

  https://agentcatalog.com/spec/agent-processes

Sections 6 (the phase graph), 6.5.1 (exception edges), 6.7.1 (deviations),
7 (automation) and 8 (handoffs) are the ones this conversion turns on.

Then read the current documentation for the primitives you will need, rather
than relying on what you remember of the API:

  https://adk.dev/graphs/routes/
    nodes, tuple chains, Event(route=), JoinNode, back-edges
  https://adk.dev/graphs/human-input/
    RequestInput and the rerun_on_resume handoff
  https://adk.dev/runtime/resume/
    ResumabilityConfig, resuming by invocation id, at-least-once tools
  https://adk.dev/graphs/data-handling/
    Event.output against state, and the selector syntax in instructions

WHAT THE DOCUMENT ASKS FOR

These hold wherever the process lands, and they matter more than style.

1. Each phase under `phases:` becomes one step, and keeps its name.

2. `after:` gives the edges. `after: a + b` is a join and waits for BOTH.
   Reading it as "either" is the defect the specification calls out by name.

3. Every handoff carries a key in square brackets. Each key becomes one field
   on the run's state, named exactly as the key with hyphens turned into
   underscores, and the sentence beside it becomes that field's comment. The key
   is the stable name; the sentence is prose that may be rewritten.

4. A phase MUST NOT begin before its inbound handoff exists. Where that is
   checkable, check it in the step rather than assuming it.

5. `automation: never` is a gate a person signs. The run stops there and does
   not continue until a person's decision comes back. Do not turn one into a
   notification, a log line, or an automatic transition, whatever the queue
   looks like.

6. Each line under `deviations:` is a backward or sideways edge, returning to
   the phase named on the right. The key in brackets names it, and that name
   belongs in the code.

7. A phase whose `after:` reads like "X or Y, whichever could not finish" is an
   exception edge: it is entered when those phases FAIL, not when they succeed.
   Do not wire it as an ordinary successor.

8. Anything in angle brackets is a blank the adopting organization fills in.
   Leave each one as a named constant at the top of the file with a TODO. Do not
   invent a value, a threshold or a date.

9. Record the document's `from:` line at the top of the file, so it says which
   reference process and which version it was generated from.

10. Run-scoped lines under `run-scoped:` are work that runs alongside the whole
    process rather than at one point in it, and a run may not close while one is
    unfinished. Say in the code what you did about them, including if the answer
    is that the runtime has nowhere to put them.

HOW THAT LOOKS IN GOOGLE ADK

11. Build a `Workflow` from `google.adk.workflow`, and pin `google-adk>=2.0` in
    a comment. Do not use `SequentialAgent`, `ParallelAgent` or `LoopAgent`: they
    are deprecated in favour of the graph, and they carry their own defects around
    state and control flow. The documentation moved to adk.dev, and anything you
    remember about nesting agents rather than drawing a graph is out of date.

12. Each phase is one node keeping its name. Take the node kind from how the
    phase resolves rather than from taste: a `human:` or `system:` phase is a plain
    Python function node, and a `runs` or `convenes` phase is an `Agent`.

13. `after:` gives the edges, written as tuple chains in `edges=[...]`, and the
    trigger is the `"START"` keyword. Take the order only from `after:` lines and
    never from the order the phases are listed in.

14. `after: a + b` is a `JoinNode`, and it must be guarded, because this is the
    worst trap of any runtime here. The join fires when every static predecessor is
    marked COMPLETED, nothing ever un-completes a node, and stored outputs are
    never cleared. So after a deviation re-runs one arm, the join fires the instant
    that arm finishes and hands the next phase LAST PASS'S value for every arm that
    did not re-run. It does not stall, it proceeds with stale data, and nothing
    logs. Stamp each arm's output with a pass counter or a content hash, and have
    the phase after the join compare the stamps and refuse to run when they
    disagree.

15. Each line under `deviations:` is a routed back-edge: a router after the
    phase on the left returning `Event(route=...)`, named after the key in
    brackets, with one arm going back to the phase on the right and one going
    forward. An unconditional cycle raises at construction, which is the one place
    this model checks your work. Nothing budgets a routed cycle, so add your own
    count and stop rather than looping forever.

16. Give every router an explicit `DEFAULT_ROUTE` arm, and route it to a phase
    that stops and asks a person. A route value matching no key writes a log
    warning, ends that branch, and lets the run finish reporting success with the
    rest of the process never having happened.

17. `automation: never` is a `RequestInput` node of its own, never an `Agent`
    asking a question. Decorate it `@node(rerun_on_resume=False)` and yield
    `RequestInput(message=..., payload=..., response_schema=...)`, so the run
    stops, persists, and delivers the person's answer to the node's successor as
    its typed input. A resumed workflow runs its tools at least once, so any
    irreversible act needs its own duplicate guard.

18. Make the gates durable or say plainly that they are not. Wrap the graph in
    `App(..., resumability_config=ResumabilityConfig(is_resumable=True))` and pass
    a persisting session service, never the in-memory one. Note in the file that
    the command line and the web UI cannot resume a run, so whoever releases these
    gates needs an operator surface that somebody has to write.

19. Every `Agent` in the graph gets `mode="single_turn"` and no `sub_agents`.
    A non-empty `sub_agents` list silently adds a transfer tool, and a model that
    uses it runs a different agent in this node's place while the graph's outgoing
    edge fires on schedule regardless: the topology is honoured perfectly and the
    work belongs to somebody else.

20. Model failure as a route, not as an exception. A node that raises does not
    propagate: the failure is caught, recorded, and shuts the workflow down without
    raising to the caller. So a phase that can fail catches its own failure and
    returns `Event(route="could-not-finish")`, and the exception phase hangs off
    that arm.

21. Keep every blank as a named module-level constant and never interpolate one
    into an `instruction=` string. Angle brackets and curly braces are ADK's own
    data selector syntax inside instructions, so a blank pasted verbatim stops
    being a blank and becomes a selector.

22. `by:` and `not-before:` have no expression, and `@node(timeout=)` is not
    one: it is an in-process wall clock that cancels the node and, because failures
    are swallowed, ends the run silently rather than recording a missed deadline.
    Nothing in `run-scoped:` has an expression either, and it must not be faked as
    an ordinary node, because a node has to be reached and has to finish before
    anything downstream starts, which is the opposite of what those lines mean.
    Leave both out of the graph and name them in the fidelity note.

Produce a second file alongside it, `FIDELITY.md`, and treat it as the more
important of the two. The code is for whoever builds this. The fidelity note
is for whoever has to decide whether this platform suits the process at all,
and that is usually a different person who will never read the code.

It has three parts.

**What came across.** Briefly: how many phases became steps, how many handoff
keys became state fields, which gates stop the run, which deviations became
edges. Counts and names, not reassurance.

**What did not, and what was done instead.** One entry per gap. For each one,
say what the document requires, what the platform can actually express, what
you did in its place, and what breaks if somebody later removes your
workaround. This last part matters most: a workaround nobody understands is a
workaround somebody deletes.

**What a person still has to decide.** The blanks are not a translation
failure, they are the point of a reference process, so list what has to be
filled in before this could run against anything real, and say which of those
choices the platform constrains.

Write it in plain English for somebody who has not read the specification, and
do not soften it. A translation of a reference process is a draft to argue
with, not a build artifact, and the honest account of what was lost is the most
useful thing you will produce.

Here is the process document.

```
PROCESS: test ad creative              id: <team>/test-ad-creative   v1
from: ref/mkt/test-ad-creative v1
owner: <who>                          effective: <date>
trigger: a performance question is raised against creative that is
         already running in <your paid channels>
         watch: record=<running creative> system=<your paid channels>
                change=<a performance question is raised against
                creative that is already running>
concurrency: runs may overlap - <how many> live at once, and
             <how many> against one audience
goal: one element of the running creative tested against variants of
      it, and a winner, a no difference, or an unfinished test recorded
      against the evidence bar that was written before launch
phases:
  take-in-question  - human: write down the performance question and
                      what a clear answer would change
                      owner: campaign-manager    after: trigger
                      automation: <level>
  read-current      - runs collect-and-report: what the running creative
                      delivers now, placement by placement, and how much
                      it varies from week to week
                      owner: analytics           after: take-in-question
                      by: <days>                 automation: <level>
  name-the-change   - convenes decide-and-announce: the one element the
                      test changes and what it is meant to improve
                      owner: campaign-manager    after: read-current
                      by: <days>                 automation: <level>
  design-comparison - human: how many variants, how the traffic splits
                      between them, and which placements carry the test
                      owner: media-buyer         after: name-the-change
                      by: <days>                 automation: <level>
  set-evidence-bar  - human: the minimum exposure per variant, the
                      minimum length of the run, the size of difference
                      that counts, and the conversion it is read from
                      owner: analytics
                      after: design-comparison
                      by: <days>                 automation: <level>
  commit-budget     - human: what buying that much exposure costs, and
                      whether the answer is worth the money. <who>
                      commits it
                      owner: campaign-manager    after: set-evidence-bar
                      automation: <level>
  brief-makers      - convenes briefing: every maker hears the same
                      description of the one element under test and what
                      has to stay identical to the running creative
                      owner: creative-producer   after: commit-budget
                      automation: <level>
  produce-variants  - runs build-by-talent: each variant made and sized
                      for every placement the test covers
                      owner: creative-producer   after: brief-makers
                      by: <days>                 automation: <level>
  check-variant-set - runs assessment: each variant read against the
                      test design, to find any variant that differs from
                      the running creative in more than one element
                      owner: buy-check           after: produce-variants
                      by: <days>                 automation: <level>
  get-sign-offs     - convenes approval: brand, disclosure and legal
                      sign, as named signers, against a version of every
                      variant in the set
                      owner: <your legal role>
                      after: check-variant-set
                      by: <days>                 automation: never
  wire-measurement  - human: one conversion, defined once, and a tag on
                      each variant that keeps its results separate for
                      the whole run
                      owner: conversion-tracker  after: commit-budget
                      by: launch                 automation: <level>
  check-before-on   - runs assessment: the configured test read against
                      the design, covering the split, the placements,
                      the variants loaded and the tag on each of them
                      owner: buy-check
                      after: get-sign-offs + wire-measurement
                      by: launch                 automation: <level>
  launch-test       - human: the buyer turns the variants on at the
                      agreed split, and the run records the date and
                      hour the exposure count starts from
                      owner: media-buyer         after: check-before-on
                      automation: <level>
  watch-delivery    - runs assessment: what each variant was actually
                      served, read against the split the design set
                      owner: buy-check           after: launch-test
                      every: <cadence>           automation: <level>
  read-the-result   - runs collect-and-report: exposure per variant, the
                      length of the run so far, and each variant's
                      conversion rate with its source beside it
                      owner: analytics           after: watch-delivery
                      every: <cadence>           automation: <level>
  call-the-winner   - convenes decide-and-announce: the numbers read
                      against the bar, ending in a winner, a recorded no
                      difference, or a decision to keep running
                      owner: campaign-manager    after: read-the-result
                      automation: <level>
  roll-out-winner   - human: the winning variant replaces the running
                      creative in every placement the test covered, and
                      the losing variants come off
                      owner: media-buyer         after: call-the-winner
                      by: <days>                 automation: <level>
  record-learnings  - convenes debrief: what was changed, what it cost,
                      what the test settled, and what to test next
                      owner: campaign-manager    after: roll-out-winner
                      automation: <level>
run-scoped:
  spend    - runs allocate-and-reconcile       owner: media-buyer
             cap: <n>/day
             from: launch-test   until: run close
  delivery - runs collect-and-report           owner: analytics
             every: <cadence>
             from: launch-test   until: run close
handoffs:
  take-in-question -> read-current [performance-question]: the
    question, written so that a number can answer it
  read-current -> name-the-change [current-performance]: what the
    running creative delivers now and how much it moves week to week,
    which is the figure the gap in the bar is set against
  name-the-change -> design-comparison [element-under-test]: the one
    element under test and what it is meant to improve
  design-comparison -> set-evidence-bar [comparison-design]: the number
    of variants, the split and the placements, because how much
    exposure the test needs depends on all three
  set-evidence-bar -> commit-budget [evidence-bar]: the minimum
    exposure, the minimum run length, the size of the gap and the
    conversion, at a version
  commit-budget -> brief-makers / wire-measurement [committed-test]:
    the same committed test. Both branches read one record
  brief-makers -> produce-variants [variant-brief]: the element that
    changes, and everything that has to stay identical to the running
    creative
  produce-variants -> check-variant-set [variant-set]: every variant at
    a version, beside the running creative it is being compared with
  check-variant-set -> get-sign-offs [variant-scores]: the scored set,
    with the design line behind every failure
  get-sign-offs -> check-before-on [approved-variants]: the approved
    variants at the signed version. A variant changed afterward voids
    the approval and sign-offs run again
  wire-measurement -> check-before-on [measurement-setup]: the
    conversion definition and the tag each variant carries
  check-before-on -> launch-test [checked-configuration]: the scored
    configuration, with the design line or the rule behind every
    failure
  launch-test -> watch-delivery [switch-on-record]: the date and hour
    the count starts from, and the split as configured
  watch-delivery -> read-the-result [served-split]: what each variant
    was served, so the result is read only over the period the split
    actually held
  read-the-result -> call-the-winner [result-reading]: exposure per
    variant, run length and conversion rate, each line attributed to
    its source
  call-the-winner -> roll-out-winner [winning-variant]: the winning
    variant at its signed version, and the placements it replaces the
    running creative in
  call-the-winner -> record-learnings [the-call-and-the-bar]: the call,
    its date, and the four parts of the bar with what each one stood at
    when the call was made
deviations:
  check-variant-set -> produce-variants [more-than-one-difference]: a
    variant differs from the running creative in more than the element
    under test, so it is made again
  get-sign-offs -> produce-variants [sign-off-changes]: a signer asks
    for changes, so the variants they named are made again and go back
    through the check on the set
  check-before-on -> wire-measurement [wrong-tag]: a variant carries
    the wrong tag, so the measurement is wired again before anything
    switches on
  check-before-on -> produce-variants [variant-rejected]: a platform
    rejects a variant on policy, so it is rewritten or that arm of the
    test is dropped
  watch-delivery -> launch-test [split-does-not-hold]: the platform
    stopped serving the variants at the agreed split, so the buyer
    resets it and the exposure count starts again from the moment the
    split holds
  call-the-winner -> watch-delivery [bar-not-met-yet]: not every part
    of the bar has been met, so the test keeps running and the numbers
    are read again
  call-the-winner -> record-learnings [no-variant-won]: the bar is met
    and no variant beat the running creative, so the run records a no
    difference and passes over the roll-out, leaving the running
    creative in every placement it already had
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for the budget, brand and legal
           agents>
  systems: ad platforms (write, cap: <n>/day),
           analytics (write: the conversion definition and the variant
           tags; read: reporting),
           the asset store (write),
           the media plan record (read),
           the placement and delivery record (read),
           the test record (write)
  data:    brand guidelines <version>, <your claims register>,
           the disclosure rules for <each market the ads run in>
           <version>, the running creative and what it delivers now,
           the test design and the evidence bar at their versions
policy:
  the evidence bar is written down before any money is spent, and no
    agent changes it once the test is live
  a variant that differs from the running creative in more than the
    element under test never launches
  sign-off is a human gate and is never delegated to an agent
  a variant changed after sign-off goes back through sign-offs
  the conversion the result is read from is never redefined while the
    test is running
  a winner is called only when all four parts of the bar have been met
  no more than <how many> tests run against one audience at once
  a test that runs out of budget before the bar is met is recorded as
    unfinished, and its numbers are never reported as a result
measures:
  cycle time: <target> from the question to the winner being live
  exposure: impressions per variant when the call was made, against <n>
  run length: days live when the call was made, against <n>
  decisiveness: the share of tests ending in a winner or a recorded no
                difference, against <target>
  quality gate: no winner is called before the bar is met
```