Manage Crisis Communication

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: crisis communication         id: <team>/crisis-communication   v1
from: ref/mkt/crisis-communication v1
owner: <who>                          effective: <date>
trigger: an incident that will become public is reported to <your
         escalation channel>
         watch: record=<incident>
                system=<your escalation channel>
                change=<an incident is reported as one that will
                become public>
concurrency: one response per incident - <how many> live at once
goal: a response issued on every channel the incident reaches, saying
      the same thing to every audience, corrected when the facts move,
      and reviewed afterwards against what was known at each point
phases:
  take-in-incident  - human: write down what happened, the time it was
                      reported, who reported it, and who already knows
                      owner: comms-manager      after: trigger
                      automation: <level>
  confirm-facts     - convenes briefing: the people handling the
                      incident say what is established and what is not
                      owner: comms-manager      after: take-in-incident
                      by: <hours>               automation: <level>
  size-exposure     - human: who is affected, which audiences have to
                      hear it, and how far the story is likely to reach
                      owner: comms-manager      after: take-in-incident
                      by: <hours>               automation: <level>
  holding-line      - human: a short first statement saying only what is
                      established, signed by <who> before it goes out
                      owner: comms-manager      after: size-exposure
                      by: <hours>               automation: never
  decide-position   - convenes decide-and-announce: <who> decides what
                      the organization will say about what happened
                      owner: <who decides>
                      after: confirm-facts + holding-line
                      by: <hours>               automation: never
  draft-statement   - human: the words the organization will say, at a
                      version, every fact carrying the source under it
                      owner: copywriter         after: decide-position
                      by: <hours>               automation: <level>
  tailor-audiences  - runs build-by-talent: the press, the customer, the
                      staff and the partner version, all saying the same
                      thing
                      owner: comms-manager      after: draft-statement
                      by: <hours>               automation: <level>
  get-sign-offs     - convenes approval: legal and <who> sign, as named
                      signers, against a version of the exact wording
                      owner: <your legal role>  after: tailor-audiences
                      by: <hours>               automation: never
  brief-speakers    - convenes briefing: everyone who may be asked hears
                      the approved answers and where the rest goes
                      owner: comms-manager      after: get-sign-offs
                      by: <hours>               automation: <level>
  notify-staff      - human: staff are told before the statement reaches
                      the press, and are told where their questions go
                      owner: comms-manager      after: get-sign-offs
                      automation: <level>
  issue-response    - human: <who> says go, and the statement goes out
                      on every channel the exposure named
                      owner: comms-manager
                      after: brief-speakers + notify-staff
                      automation: never
  answer-questions  - human: reporters, customers and the public get
                      answers taken from the approved wording
                      owner: comms-manager      after: issue-response
                      automation: <level>
  track-coverage    - runs collect-and-report: what ran, where it ran,
                      when it appeared, and what it actually said
                      owner: coverage-monitor   after: take-in-incident
                      every: <interval>         automation: <level>
  update-response   - human: a new fact, or a published fact that is
                      wrong, changes the wording at a new version
                      owner: comms-manager      after: track-coverage
                      by: <hours>               automation: <level>
  close-response    - human: <who> says the active response is over and
                      names who holds the standing answers afterwards
                      owner: <who decides>
                      after: answer-questions + track-coverage
                      automation: never
  review-response   - convenes debrief: what was known at each point,
                      what was said, and what changes before next time
                      owner: comms-manager      after: close-response
                      by: <days>                automation: <level>
run-scoped:
  status  - runs roll-call                      owner: comms-manager
            every: <interval>
            from: take-in-incident   until: close-response
  numbers - runs collect-and-report             owner: analytics
            every: <interval>
            from: issue-response   until: run close
handoffs:
  take-in-incident -> confirm-facts [incident-report]: what was
    reported, the time it was reported, and who already knows
  take-in-incident -> size-exposure [incident-record]: the same
    record. Both branches read one incident record
  take-in-incident -> track-coverage [what-to-watch-for]: what to
    watch for, before anything has been said
  confirm-facts -> decide-position [established-facts]: what is
    established, what is still open, and the time each fact was
    established
  size-exposure -> holding-line [audiences-to-reach]: the audiences
    that have to hear something, and how soon each one has to hear it
  holding-line -> decide-position [words-already-said]: the words
    already said in public, which the position has to hold
  decide-position -> draft-statement [agreed-position]: the position a
    named person decided, and the questions that stay unanswered on
    purpose
  draft-statement -> tailor-audiences [master-statement]: the statement
    at a version, every fact carrying its source and the time it was
    established
  tailor-audiences -> get-sign-offs [audience-versions]: the four
    versions under one version number, so the signers read them
    against each other
  get-sign-offs -> brief-speakers [approved-wording]: the approved
    wording at the signed version, and the questions it does not answer
  get-sign-offs -> notify-staff [staff-version]: the staff version at
    the signed version
  brief-speakers -> issue-response [speaking-rules]: who may speak, on
    what, and where every other question is sent
  issue-response -> answer-questions [what-went-out]: what went out, on
    which channel, at what time
  issue-response -> track-coverage [issued-record]: the same record, so
    a mention can be traced back to what was sent
  track-coverage -> update-response [coverage-found]: what ran, quoted,
    with anything wrong set beside the source that corrects it
  update-response -> get-sign-offs [changed-wording]: the changed
    wording at a new version, because a change voids the approval
  close-response -> review-response [response-timeline]: the timeline
    at its final version, and every version of every audience's wording
deviations:
  track-coverage -> holding-line [story-already-broken]: the story
    breaks before the facts are confirmed, so the holding line goes
    out saying only what is established by then
  decide-position -> holding-line [no-position-agreed]: no position is
    agreed, so the holding line stands as the last thing said and
    nothing further goes out
  get-sign-offs -> draft-statement [sign-off-changes]: a signer comes
    back with changes, and only the part they named reopens
  get-sign-offs -> decide-position [position-in-question]: a signer
    objects to the position itself, so a person decides it again
  answer-questions -> draft-statement [question-not-covered]: a
    question arrives that the approved wording does not answer, and
    the answer worth giving is drafted and signed like any other
  update-response -> confirm-facts [incident-gets-worse]: the incident
    gets worse while the response is live, so the facts are confirmed
    again and the run walks forward from there
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for leadership, legal, the expert and
           the spokesperson>
  systems: the incident record (read), the message record (write),
           the announcement timeline (write), the website (write),
           the outbound mail system (write), the social inboxes (write),
           the press and analyst contact record (write),
           the coverage record (write), analytics (read),
           the staged releases (trigger)
  data:    brand guidelines <version>, <your claims register>,
           <your standing crisis plan> <version>, the incident record
policy:
  a person decides what the organization says, at every version
  nothing goes out unsigned, and the holding line counts as something
    going out
  wording changed after sign-off goes back through sign-offs
  no agent answers a question the approved wording does not cover, and an
    unanswerable question goes to <who> within <how long>
  a fact that turns out to be wrong is corrected in a new version, and
    the version it corrects stays where it is
  every audience is told the same thing, and staff are told before the
    press
  no agent asks an outside publication for a correction - <who> decides
    whether to ask, and a person asks
  an incident that reaches a regulator, a customer's data or somebody's
    safety goes to <who> before anything is said in public
measures:
  cycle time: <target> from the incident report to the holding line, and
              <target> from the incident report to the full response
  volume: <responses per period>
  quality gate: nothing goes out unsigned, and every fact in what goes
                out carries the time it was established
```

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: crisis communication         id: <team>/crisis-communication   v1
from: ref/mkt/crisis-communication v1
owner: <who>                          effective: <date>
trigger: an incident that will become public is reported to <your
         escalation channel>
         watch: record=<incident>
                system=<your escalation channel>
                change=<an incident is reported as one that will
                become public>
concurrency: one response per incident - <how many> live at once
goal: a response issued on every channel the incident reaches, saying
      the same thing to every audience, corrected when the facts move,
      and reviewed afterwards against what was known at each point
phases:
  take-in-incident  - human: write down what happened, the time it was
                      reported, who reported it, and who already knows
                      owner: comms-manager      after: trigger
                      automation: <level>
  confirm-facts     - convenes briefing: the people handling the
                      incident say what is established and what is not
                      owner: comms-manager      after: take-in-incident
                      by: <hours>               automation: <level>
  size-exposure     - human: who is affected, which audiences have to
                      hear it, and how far the story is likely to reach
                      owner: comms-manager      after: take-in-incident
                      by: <hours>               automation: <level>
  holding-line      - human: a short first statement saying only what is
                      established, signed by <who> before it goes out
                      owner: comms-manager      after: size-exposure
                      by: <hours>               automation: never
  decide-position   - convenes decide-and-announce: <who> decides what
                      the organization will say about what happened
                      owner: <who decides>
                      after: confirm-facts + holding-line
                      by: <hours>               automation: never
  draft-statement   - human: the words the organization will say, at a
                      version, every fact carrying the source under it
                      owner: copywriter         after: decide-position
                      by: <hours>               automation: <level>
  tailor-audiences  - runs build-by-talent: the press, the customer, the
                      staff and the partner version, all saying the same
                      thing
                      owner: comms-manager      after: draft-statement
                      by: <hours>               automation: <level>
  get-sign-offs     - convenes approval: legal and <who> sign, as named
                      signers, against a version of the exact wording
                      owner: <your legal role>  after: tailor-audiences
                      by: <hours>               automation: never
  brief-speakers    - convenes briefing: everyone who may be asked hears
                      the approved answers and where the rest goes
                      owner: comms-manager      after: get-sign-offs
                      by: <hours>               automation: <level>
  notify-staff      - human: staff are told before the statement reaches
                      the press, and are told where their questions go
                      owner: comms-manager      after: get-sign-offs
                      automation: <level>
  issue-response    - human: <who> says go, and the statement goes out
                      on every channel the exposure named
                      owner: comms-manager
                      after: brief-speakers + notify-staff
                      automation: never
  answer-questions  - human: reporters, customers and the public get
                      answers taken from the approved wording
                      owner: comms-manager      after: issue-response
                      automation: <level>
  track-coverage    - runs collect-and-report: what ran, where it ran,
                      when it appeared, and what it actually said
                      owner: coverage-monitor   after: take-in-incident
                      every: <interval>         automation: <level>
  update-response   - human: a new fact, or a published fact that is
                      wrong, changes the wording at a new version
                      owner: comms-manager      after: track-coverage
                      by: <hours>               automation: <level>
  close-response    - human: <who> says the active response is over and
                      names who holds the standing answers afterwards
                      owner: <who decides>
                      after: answer-questions + track-coverage
                      automation: never
  review-response   - convenes debrief: what was known at each point,
                      what was said, and what changes before next time
                      owner: comms-manager      after: close-response
                      by: <days>                automation: <level>
run-scoped:
  status  - runs roll-call                      owner: comms-manager
            every: <interval>
            from: take-in-incident   until: close-response
  numbers - runs collect-and-report             owner: analytics
            every: <interval>
            from: issue-response   until: run close
handoffs:
  take-in-incident -> confirm-facts [incident-report]: what was
    reported, the time it was reported, and who already knows
  take-in-incident -> size-exposure [incident-record]: the same
    record. Both branches read one incident record
  take-in-incident -> track-coverage [what-to-watch-for]: what to
    watch for, before anything has been said
  confirm-facts -> decide-position [established-facts]: what is
    established, what is still open, and the time each fact was
    established
  size-exposure -> holding-line [audiences-to-reach]: the audiences
    that have to hear something, and how soon each one has to hear it
  holding-line -> decide-position [words-already-said]: the words
    already said in public, which the position has to hold
  decide-position -> draft-statement [agreed-position]: the position a
    named person decided, and the questions that stay unanswered on
    purpose
  draft-statement -> tailor-audiences [master-statement]: the statement
    at a version, every fact carrying its source and the time it was
    established
  tailor-audiences -> get-sign-offs [audience-versions]: the four
    versions under one version number, so the signers read them
    against each other
  get-sign-offs -> brief-speakers [approved-wording]: the approved
    wording at the signed version, and the questions it does not answer
  get-sign-offs -> notify-staff [staff-version]: the staff version at
    the signed version
  brief-speakers -> issue-response [speaking-rules]: who may speak, on
    what, and where every other question is sent
  issue-response -> answer-questions [what-went-out]: what went out, on
    which channel, at what time
  issue-response -> track-coverage [issued-record]: the same record, so
    a mention can be traced back to what was sent
  track-coverage -> update-response [coverage-found]: what ran, quoted,
    with anything wrong set beside the source that corrects it
  update-response -> get-sign-offs [changed-wording]: the changed
    wording at a new version, because a change voids the approval
  close-response -> review-response [response-timeline]: the timeline
    at its final version, and every version of every audience's wording
deviations:
  track-coverage -> holding-line [story-already-broken]: the story
    breaks before the facts are confirmed, so the holding line goes
    out saying only what is established by then
  decide-position -> holding-line [no-position-agreed]: no position is
    agreed, so the holding line stands as the last thing said and
    nothing further goes out
  get-sign-offs -> draft-statement [sign-off-changes]: a signer comes
    back with changes, and only the part they named reopens
  get-sign-offs -> decide-position [position-in-question]: a signer
    objects to the position itself, so a person decides it again
  answer-questions -> draft-statement [question-not-covered]: a
    question arrives that the approved wording does not answer, and
    the answer worth giving is drafted and signed like any other
  update-response -> confirm-facts [incident-gets-worse]: the incident
    gets worse while the response is live, so the facts are confirmed
    again and the run walks forward from there
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for leadership, legal, the expert and
           the spokesperson>
  systems: the incident record (read), the message record (write),
           the announcement timeline (write), the website (write),
           the outbound mail system (write), the social inboxes (write),
           the press and analyst contact record (write),
           the coverage record (write), analytics (read),
           the staged releases (trigger)
  data:    brand guidelines <version>, <your claims register>,
           <your standing crisis plan> <version>, the incident record
policy:
  a person decides what the organization says, at every version
  nothing goes out unsigned, and the holding line counts as something
    going out
  wording changed after sign-off goes back through sign-offs
  no agent answers a question the approved wording does not cover, and an
    unanswerable question goes to <who> within <how long>
  a fact that turns out to be wrong is corrected in a new version, and
    the version it corrects stays where it is
  every audience is told the same thing, and staff are told before the
    press
  no agent asks an outside publication for a correction - <who> decides
    whether to ask, and a person asks
  an incident that reaches a regulator, a customer's data or somebody's
    safety goes to <who> before anything is said in public
measures:
  cycle time: <target> from the incident report to the holding line, and
              <target> from the incident report to the full response
  volume: <responses per period>
  quality gate: nothing goes out unsigned, and every fact in what goes
                out carries the time it was established
```

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: crisis communication         id: <team>/crisis-communication   v1
from: ref/mkt/crisis-communication v1
owner: <who>                          effective: <date>
trigger: an incident that will become public is reported to <your
         escalation channel>
         watch: record=<incident>
                system=<your escalation channel>
                change=<an incident is reported as one that will
                become public>
concurrency: one response per incident - <how many> live at once
goal: a response issued on every channel the incident reaches, saying
      the same thing to every audience, corrected when the facts move,
      and reviewed afterwards against what was known at each point
phases:
  take-in-incident  - human: write down what happened, the time it was
                      reported, who reported it, and who already knows
                      owner: comms-manager      after: trigger
                      automation: <level>
  confirm-facts     - convenes briefing: the people handling the
                      incident say what is established and what is not
                      owner: comms-manager      after: take-in-incident
                      by: <hours>               automation: <level>
  size-exposure     - human: who is affected, which audiences have to
                      hear it, and how far the story is likely to reach
                      owner: comms-manager      after: take-in-incident
                      by: <hours>               automation: <level>
  holding-line      - human: a short first statement saying only what is
                      established, signed by <who> before it goes out
                      owner: comms-manager      after: size-exposure
                      by: <hours>               automation: never
  decide-position   - convenes decide-and-announce: <who> decides what
                      the organization will say about what happened
                      owner: <who decides>
                      after: confirm-facts + holding-line
                      by: <hours>               automation: never
  draft-statement   - human: the words the organization will say, at a
                      version, every fact carrying the source under it
                      owner: copywriter         after: decide-position
                      by: <hours>               automation: <level>
  tailor-audiences  - runs build-by-talent: the press, the customer, the
                      staff and the partner version, all saying the same
                      thing
                      owner: comms-manager      after: draft-statement
                      by: <hours>               automation: <level>
  get-sign-offs     - convenes approval: legal and <who> sign, as named
                      signers, against a version of the exact wording
                      owner: <your legal role>  after: tailor-audiences
                      by: <hours>               automation: never
  brief-speakers    - convenes briefing: everyone who may be asked hears
                      the approved answers and where the rest goes
                      owner: comms-manager      after: get-sign-offs
                      by: <hours>               automation: <level>
  notify-staff      - human: staff are told before the statement reaches
                      the press, and are told where their questions go
                      owner: comms-manager      after: get-sign-offs
                      automation: <level>
  issue-response    - human: <who> says go, and the statement goes out
                      on every channel the exposure named
                      owner: comms-manager
                      after: brief-speakers + notify-staff
                      automation: never
  answer-questions  - human: reporters, customers and the public get
                      answers taken from the approved wording
                      owner: comms-manager      after: issue-response
                      automation: <level>
  track-coverage    - runs collect-and-report: what ran, where it ran,
                      when it appeared, and what it actually said
                      owner: coverage-monitor   after: take-in-incident
                      every: <interval>         automation: <level>
  update-response   - human: a new fact, or a published fact that is
                      wrong, changes the wording at a new version
                      owner: comms-manager      after: track-coverage
                      by: <hours>               automation: <level>
  close-response    - human: <who> says the active response is over and
                      names who holds the standing answers afterwards
                      owner: <who decides>
                      after: answer-questions + track-coverage
                      automation: never
  review-response   - convenes debrief: what was known at each point,
                      what was said, and what changes before next time
                      owner: comms-manager      after: close-response
                      by: <days>                automation: <level>
run-scoped:
  status  - runs roll-call                      owner: comms-manager
            every: <interval>
            from: take-in-incident   until: close-response
  numbers - runs collect-and-report             owner: analytics
            every: <interval>
            from: issue-response   until: run close
handoffs:
  take-in-incident -> confirm-facts [incident-report]: what was
    reported, the time it was reported, and who already knows
  take-in-incident -> size-exposure [incident-record]: the same
    record. Both branches read one incident record
  take-in-incident -> track-coverage [what-to-watch-for]: what to
    watch for, before anything has been said
  confirm-facts -> decide-position [established-facts]: what is
    established, what is still open, and the time each fact was
    established
  size-exposure -> holding-line [audiences-to-reach]: the audiences
    that have to hear something, and how soon each one has to hear it
  holding-line -> decide-position [words-already-said]: the words
    already said in public, which the position has to hold
  decide-position -> draft-statement [agreed-position]: the position a
    named person decided, and the questions that stay unanswered on
    purpose
  draft-statement -> tailor-audiences [master-statement]: the statement
    at a version, every fact carrying its source and the time it was
    established
  tailor-audiences -> get-sign-offs [audience-versions]: the four
    versions under one version number, so the signers read them
    against each other
  get-sign-offs -> brief-speakers [approved-wording]: the approved
    wording at the signed version, and the questions it does not answer
  get-sign-offs -> notify-staff [staff-version]: the staff version at
    the signed version
  brief-speakers -> issue-response [speaking-rules]: who may speak, on
    what, and where every other question is sent
  issue-response -> answer-questions [what-went-out]: what went out, on
    which channel, at what time
  issue-response -> track-coverage [issued-record]: the same record, so
    a mention can be traced back to what was sent
  track-coverage -> update-response [coverage-found]: what ran, quoted,
    with anything wrong set beside the source that corrects it
  update-response -> get-sign-offs [changed-wording]: the changed
    wording at a new version, because a change voids the approval
  close-response -> review-response [response-timeline]: the timeline
    at its final version, and every version of every audience's wording
deviations:
  track-coverage -> holding-line [story-already-broken]: the story
    breaks before the facts are confirmed, so the holding line goes
    out saying only what is established by then
  decide-position -> holding-line [no-position-agreed]: no position is
    agreed, so the holding line stands as the last thing said and
    nothing further goes out
  get-sign-offs -> draft-statement [sign-off-changes]: a signer comes
    back with changes, and only the part they named reopens
  get-sign-offs -> decide-position [position-in-question]: a signer
    objects to the position itself, so a person decides it again
  answer-questions -> draft-statement [question-not-covered]: a
    question arrives that the approved wording does not answer, and
    the answer worth giving is drafted and signed like any other
  update-response -> confirm-facts [incident-gets-worse]: the incident
    gets worse while the response is live, so the facts are confirmed
    again and the run walks forward from there
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for leadership, legal, the expert and
           the spokesperson>
  systems: the incident record (read), the message record (write),
           the announcement timeline (write), the website (write),
           the outbound mail system (write), the social inboxes (write),
           the press and analyst contact record (write),
           the coverage record (write), analytics (read),
           the staged releases (trigger)
  data:    brand guidelines <version>, <your claims register>,
           <your standing crisis plan> <version>, the incident record
policy:
  a person decides what the organization says, at every version
  nothing goes out unsigned, and the holding line counts as something
    going out
  wording changed after sign-off goes back through sign-offs
  no agent answers a question the approved wording does not cover, and an
    unanswerable question goes to <who> within <how long>
  a fact that turns out to be wrong is corrected in a new version, and
    the version it corrects stays where it is
  every audience is told the same thing, and staff are told before the
    press
  no agent asks an outside publication for a correction - <who> decides
    whether to ask, and a person asks
  an incident that reaches a regulator, a customer's data or somebody's
    safety goes to <who> before anything is said in public
measures:
  cycle time: <target> from the incident report to the holding line, and
              <target> from the incident report to the full response
  volume: <responses per period>
  quality gate: nothing goes out unsigned, and every fact in what goes
                out carries the time it was established
```

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: crisis communication         id: <team>/crisis-communication   v1
from: ref/mkt/crisis-communication v1
owner: <who>                          effective: <date>
trigger: an incident that will become public is reported to <your
         escalation channel>
         watch: record=<incident>
                system=<your escalation channel>
                change=<an incident is reported as one that will
                become public>
concurrency: one response per incident - <how many> live at once
goal: a response issued on every channel the incident reaches, saying
      the same thing to every audience, corrected when the facts move,
      and reviewed afterwards against what was known at each point
phases:
  take-in-incident  - human: write down what happened, the time it was
                      reported, who reported it, and who already knows
                      owner: comms-manager      after: trigger
                      automation: <level>
  confirm-facts     - convenes briefing: the people handling the
                      incident say what is established and what is not
                      owner: comms-manager      after: take-in-incident
                      by: <hours>               automation: <level>
  size-exposure     - human: who is affected, which audiences have to
                      hear it, and how far the story is likely to reach
                      owner: comms-manager      after: take-in-incident
                      by: <hours>               automation: <level>
  holding-line      - human: a short first statement saying only what is
                      established, signed by <who> before it goes out
                      owner: comms-manager      after: size-exposure
                      by: <hours>               automation: never
  decide-position   - convenes decide-and-announce: <who> decides what
                      the organization will say about what happened
                      owner: <who decides>
                      after: confirm-facts + holding-line
                      by: <hours>               automation: never
  draft-statement   - human: the words the organization will say, at a
                      version, every fact carrying the source under it
                      owner: copywriter         after: decide-position
                      by: <hours>               automation: <level>
  tailor-audiences  - runs build-by-talent: the press, the customer, the
                      staff and the partner version, all saying the same
                      thing
                      owner: comms-manager      after: draft-statement
                      by: <hours>               automation: <level>
  get-sign-offs     - convenes approval: legal and <who> sign, as named
                      signers, against a version of the exact wording
                      owner: <your legal role>  after: tailor-audiences
                      by: <hours>               automation: never
  brief-speakers    - convenes briefing: everyone who may be asked hears
                      the approved answers and where the rest goes
                      owner: comms-manager      after: get-sign-offs
                      by: <hours>               automation: <level>
  notify-staff      - human: staff are told before the statement reaches
                      the press, and are told where their questions go
                      owner: comms-manager      after: get-sign-offs
                      automation: <level>
  issue-response    - human: <who> says go, and the statement goes out
                      on every channel the exposure named
                      owner: comms-manager
                      after: brief-speakers + notify-staff
                      automation: never
  answer-questions  - human: reporters, customers and the public get
                      answers taken from the approved wording
                      owner: comms-manager      after: issue-response
                      automation: <level>
  track-coverage    - runs collect-and-report: what ran, where it ran,
                      when it appeared, and what it actually said
                      owner: coverage-monitor   after: take-in-incident
                      every: <interval>         automation: <level>
  update-response   - human: a new fact, or a published fact that is
                      wrong, changes the wording at a new version
                      owner: comms-manager      after: track-coverage
                      by: <hours>               automation: <level>
  close-response    - human: <who> says the active response is over and
                      names who holds the standing answers afterwards
                      owner: <who decides>
                      after: answer-questions + track-coverage
                      automation: never
  review-response   - convenes debrief: what was known at each point,
                      what was said, and what changes before next time
                      owner: comms-manager      after: close-response
                      by: <days>                automation: <level>
run-scoped:
  status  - runs roll-call                      owner: comms-manager
            every: <interval>
            from: take-in-incident   until: close-response
  numbers - runs collect-and-report             owner: analytics
            every: <interval>
            from: issue-response   until: run close
handoffs:
  take-in-incident -> confirm-facts [incident-report]: what was
    reported, the time it was reported, and who already knows
  take-in-incident -> size-exposure [incident-record]: the same
    record. Both branches read one incident record
  take-in-incident -> track-coverage [what-to-watch-for]: what to
    watch for, before anything has been said
  confirm-facts -> decide-position [established-facts]: what is
    established, what is still open, and the time each fact was
    established
  size-exposure -> holding-line [audiences-to-reach]: the audiences
    that have to hear something, and how soon each one has to hear it
  holding-line -> decide-position [words-already-said]: the words
    already said in public, which the position has to hold
  decide-position -> draft-statement [agreed-position]: the position a
    named person decided, and the questions that stay unanswered on
    purpose
  draft-statement -> tailor-audiences [master-statement]: the statement
    at a version, every fact carrying its source and the time it was
    established
  tailor-audiences -> get-sign-offs [audience-versions]: the four
    versions under one version number, so the signers read them
    against each other
  get-sign-offs -> brief-speakers [approved-wording]: the approved
    wording at the signed version, and the questions it does not answer
  get-sign-offs -> notify-staff [staff-version]: the staff version at
    the signed version
  brief-speakers -> issue-response [speaking-rules]: who may speak, on
    what, and where every other question is sent
  issue-response -> answer-questions [what-went-out]: what went out, on
    which channel, at what time
  issue-response -> track-coverage [issued-record]: the same record, so
    a mention can be traced back to what was sent
  track-coverage -> update-response [coverage-found]: what ran, quoted,
    with anything wrong set beside the source that corrects it
  update-response -> get-sign-offs [changed-wording]: the changed
    wording at a new version, because a change voids the approval
  close-response -> review-response [response-timeline]: the timeline
    at its final version, and every version of every audience's wording
deviations:
  track-coverage -> holding-line [story-already-broken]: the story
    breaks before the facts are confirmed, so the holding line goes
    out saying only what is established by then
  decide-position -> holding-line [no-position-agreed]: no position is
    agreed, so the holding line stands as the last thing said and
    nothing further goes out
  get-sign-offs -> draft-statement [sign-off-changes]: a signer comes
    back with changes, and only the part they named reopens
  get-sign-offs -> decide-position [position-in-question]: a signer
    objects to the position itself, so a person decides it again
  answer-questions -> draft-statement [question-not-covered]: a
    question arrives that the approved wording does not answer, and
    the answer worth giving is drafted and signed like any other
  update-response -> confirm-facts [incident-gets-worse]: the incident
    gets worse while the response is live, so the facts are confirmed
    again and the run walks forward from there
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for leadership, legal, the expert and
           the spokesperson>
  systems: the incident record (read), the message record (write),
           the announcement timeline (write), the website (write),
           the outbound mail system (write), the social inboxes (write),
           the press and analyst contact record (write),
           the coverage record (write), analytics (read),
           the staged releases (trigger)
  data:    brand guidelines <version>, <your claims register>,
           <your standing crisis plan> <version>, the incident record
policy:
  a person decides what the organization says, at every version
  nothing goes out unsigned, and the holding line counts as something
    going out
  wording changed after sign-off goes back through sign-offs
  no agent answers a question the approved wording does not cover, and an
    unanswerable question goes to <who> within <how long>
  a fact that turns out to be wrong is corrected in a new version, and
    the version it corrects stays where it is
  every audience is told the same thing, and staff are told before the
    press
  no agent asks an outside publication for a correction - <who> decides
    whether to ask, and a person asks
  an incident that reaches a regulator, a customer's data or somebody's
    safety goes to <who> before anything is said in public
measures:
  cycle time: <target> from the incident report to the holding line, and
              <target> from the incident report to the full response
  volume: <responses per period>
  quality gate: nothing goes out unsigned, and every fact in what goes
                out carries the time it was established
```