Model the Territories

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: model the territories        id: <team>/model-the-territories   v1
from: ref/rev/model-the-territories v1
owner: <who>                          effective: <date>
trigger: the carve for <period> opens on <your planning calendar>
         watch: record=<the carve for the period>
                system=<your planning calendar>
                change=<the carve opens for the period>
concurrency: one run per period per market - a re-cut inside the period
             is a new version of the same run, not a new run
goal: every account in exactly one territory, every territory modelled
      for what it can carry, and one map fixed at a version before any
      quota is set against it
phases:
  take-in-number     - human: the target for the period, the segments it
                       covers, and the date the map has to be fixed
                       owner: territory-modeler   after: trigger
                       automation: assisted
  fix-carve-rule     - convenes decide-and-announce: what a territory is
                       cut on, whether that is geography, industry, size
                       or named accounts, decided once and written down
                       before anything is drawn
                       owner: <your revenue operations role>
                       after: take-in-number      automation: never
  take-in-accounts   - runs collect-and-report: every account the carve
                       will place, with the fields the rule reads,
                       pulled at one version of <your account record>
                       owner: analytics           after: take-in-number
                       by: <days>                 automation: autonomous
  clean-accounts     - human: duplicates merged into one account, and
                       every account whose fields the rule cannot read
                       listed by name rather than filled in by guess
                       owner: <your data steward role>
                       after: take-in-accounts
                       by: <days>                 automation: assisted
  size-accounts      - runs assessment: what each account buys today and
                       what it could carry, each figure naming the
                       system it was read from
                       owner: account-monitor     after: clean-accounts
                       by: <days>                 automation: supervised
  read-coverage      - runs collect-and-report: which patches were
                       worked last period, which were never called, and
                       what was left with no owner at all
                       owner: coverage-check
                       after: take-in-accounts    automation: autonomous
  draw-candidates    - runs build-by-talent: <how many> maps drawn on
                       the agreed rule, each one placing every account
                       exactly once
                       owner: territory-modeler
                       after: fix-carve-rule + size-accounts +
                       read-coverage
                       by: <days>                 automation: supervised
  model-carrying     - runs build-by-talent: what each patch on each map
                       can produce in the period, with the assumption
                       written beside every number
                       owner: territory-modeler   after: draw-candidates
                       by: <days>                 automation: supervised
  test-history       - runs assessment: the model run backwards over the
                       last <periods> and set beside what those patches
                       actually closed
                       owner: statistician        after: model-carrying
                       automation: supervised
  check-balance      - runs assessment: no patch above <accounts>
                       accounts or above <amount>, none below <amount>,
                       and no account sitting in two patches
                       owner: coverage-check      after: test-history
                       automation: autonomous
  cost-cuts          - runs allocate-and-reconcile: the sellers, the
                       travel and the support each map needs, priced
                       against <your cost model>
                       owner: capacity-manager    after: check-balance
                       by: <days>                 automation: supervised
  choose-cut         - convenes decide-and-announce: <who> picks one map
                       and says why. The maps not chosen are kept with
                       the reason each one lost
                       owner: <your sales leadership role>
                       after: cost-cuts           automation: never
  fix-map            - human: the chosen map at a version, with the rule
                       it was drawn on and the date it takes effect
                       owner: territory-modeler   after: choose-cut
                       by: <days>                 automation: assisted
  record-assumptions - human: the assumption under every carrying
                       number, and what would make it wrong
                       owner: territory-modeler   after: fix-map
                       automation: assisted
  hand-over-map      - human: the map, its rules and its carrying
                       numbers handed to <your quota process>
                       owner: quota-setter
                       after: record-assumptions  automation: assisted
run-scoped:
  data-quality - runs roll-call                 owner: analytics
                 every: <cadence>
                 from: take-in-accounts   until: fix-map
handoffs:
  take-in-number -> fix-carve-rule [target-and-segments]: the target,
    the segments it covers, and the date the map is due
  take-in-number -> take-in-accounts [segment-definitions]: the same
    segment definitions, so the account base is pulled on the boundaries
    the map will use
  fix-carve-rule -> draw-candidates [carve-rule]: what a territory is
    cut on, written down, and the account fields that rule reads
  take-in-accounts -> clean-accounts [account-base]: every account with
    the fields the rule needs, and the version each field was read at
  take-in-accounts -> read-coverage [accounts-for-coverage]: the same
    account base, so coverage is read against the accounts actually
    being carved
  clean-accounts -> size-accounts [clean-account-base]: one record per
    real account, with every account the rule cannot read listed by name
  size-accounts -> draw-candidates [account-sizes]: current spend and
    carrying size per account, each figure naming the system it came
    from
  read-coverage -> draw-candidates [last-period-coverage]: which patches
    were worked, which were not, and every account nobody called
  draw-candidates -> model-carrying [candidate-maps]: the candidate
    maps, each placing every account exactly once
  model-carrying -> test-history [carrying-numbers]: what each patch
    carries, with the assumption beside every number
  test-history -> check-balance [backtest-result]: the modelled numbers
    set beside what closed, and every patch the model got wrong by more
    than <percent>
  check-balance -> cost-cuts [balance-findings]: the balance finding per
    patch, with the rule behind every failure
  cost-cuts -> choose-cut [cut-costs]: what each map costs to staff and
    to work, and what it would displace
  choose-cut -> fix-map [chosen-map]: the chosen map, who chose it, and
    why
  fix-map -> record-assumptions [fixed-map]: the map at a version, with
    the rule it was drawn on and the date it takes effect
  record-assumptions -> hand-over-map [model-assumptions]: the
    assumption under every carrying number, and what would make it wrong
deviations:
  clean-accounts -> take-in-accounts [field-the-rule-reads-is-missing]:
    accounts are missing a field the rule cuts on, so the account base
    is taken in again and what stays unreadable is placed by hand
  test-history -> model-carrying [model-fails-history]: the model does
    not reproduce what those patches actually closed, so the carrying
    model is rebuilt rather than the history adjusted
  check-balance -> draw-candidates [patch-nobody-could-work]: a patch
    comes out too big, too spread or too rich for one seller, so the
    candidates are drawn again
  choose-cut -> draw-candidates [no-cut-is-workable]: every map on the
    table fails balance or cost, so the candidates are drawn again and
    the leaders are told which constraint has to move
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for the leader who chooses the map,
           the finance partner and the data steward>
  systems: <your account record> (read), the CRM (read),
           the territory map (write), the model store (write),
           the reporting warehouse (read), the coverage record (write)
  data:    the target for the period, <your segment definitions> at a
           version, the account base at a version, the last <periods>
           of closed revenue, <your cost model>
policy:
  every account sits in exactly one territory. An account in none is a
    defect, and the map does not publish with one
  what a territory is cut on is decided before any map is drawn, and a
    map drawn on a different rule is redrawn rather than argued about
  a carrying number that cannot name the data it came from is marked
    unsourced, and the map carries that mark where a reader sees it
  the map is chosen by a named person. It is never the average of the
    candidates and never the one the model scored highest
  a patch nobody has the capacity to work is named as a gap. Raising
    its number instead is the failure this process exists to prevent
  the maps that were not chosen are kept, each with the reason it lost
measures:
  cycle time: <weeks> from the number to the fixed map
  coverage: <target> share of accounts placed in a workable patch
  accuracy: each patch's modelled carrying number against what it closed
  quality gate: no map is fixed while an account is unplaced, in two
                patches, or carrying an unsourced number
```

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: model the territories        id: <team>/model-the-territories   v1
from: ref/rev/model-the-territories v1
owner: <who>                          effective: <date>
trigger: the carve for <period> opens on <your planning calendar>
         watch: record=<the carve for the period>
                system=<your planning calendar>
                change=<the carve opens for the period>
concurrency: one run per period per market - a re-cut inside the period
             is a new version of the same run, not a new run
goal: every account in exactly one territory, every territory modelled
      for what it can carry, and one map fixed at a version before any
      quota is set against it
phases:
  take-in-number     - human: the target for the period, the segments it
                       covers, and the date the map has to be fixed
                       owner: territory-modeler   after: trigger
                       automation: assisted
  fix-carve-rule     - convenes decide-and-announce: what a territory is
                       cut on, whether that is geography, industry, size
                       or named accounts, decided once and written down
                       before anything is drawn
                       owner: <your revenue operations role>
                       after: take-in-number      automation: never
  take-in-accounts   - runs collect-and-report: every account the carve
                       will place, with the fields the rule reads,
                       pulled at one version of <your account record>
                       owner: analytics           after: take-in-number
                       by: <days>                 automation: autonomous
  clean-accounts     - human: duplicates merged into one account, and
                       every account whose fields the rule cannot read
                       listed by name rather than filled in by guess
                       owner: <your data steward role>
                       after: take-in-accounts
                       by: <days>                 automation: assisted
  size-accounts      - runs assessment: what each account buys today and
                       what it could carry, each figure naming the
                       system it was read from
                       owner: account-monitor     after: clean-accounts
                       by: <days>                 automation: supervised
  read-coverage      - runs collect-and-report: which patches were
                       worked last period, which were never called, and
                       what was left with no owner at all
                       owner: coverage-check
                       after: take-in-accounts    automation: autonomous
  draw-candidates    - runs build-by-talent: <how many> maps drawn on
                       the agreed rule, each one placing every account
                       exactly once
                       owner: territory-modeler
                       after: fix-carve-rule + size-accounts +
                       read-coverage
                       by: <days>                 automation: supervised
  model-carrying     - runs build-by-talent: what each patch on each map
                       can produce in the period, with the assumption
                       written beside every number
                       owner: territory-modeler   after: draw-candidates
                       by: <days>                 automation: supervised
  test-history       - runs assessment: the model run backwards over the
                       last <periods> and set beside what those patches
                       actually closed
                       owner: statistician        after: model-carrying
                       automation: supervised
  check-balance      - runs assessment: no patch above <accounts>
                       accounts or above <amount>, none below <amount>,
                       and no account sitting in two patches
                       owner: coverage-check      after: test-history
                       automation: autonomous
  cost-cuts          - runs allocate-and-reconcile: the sellers, the
                       travel and the support each map needs, priced
                       against <your cost model>
                       owner: capacity-manager    after: check-balance
                       by: <days>                 automation: supervised
  choose-cut         - convenes decide-and-announce: <who> picks one map
                       and says why. The maps not chosen are kept with
                       the reason each one lost
                       owner: <your sales leadership role>
                       after: cost-cuts           automation: never
  fix-map            - human: the chosen map at a version, with the rule
                       it was drawn on and the date it takes effect
                       owner: territory-modeler   after: choose-cut
                       by: <days>                 automation: assisted
  record-assumptions - human: the assumption under every carrying
                       number, and what would make it wrong
                       owner: territory-modeler   after: fix-map
                       automation: assisted
  hand-over-map      - human: the map, its rules and its carrying
                       numbers handed to <your quota process>
                       owner: quota-setter
                       after: record-assumptions  automation: assisted
run-scoped:
  data-quality - runs roll-call                 owner: analytics
                 every: <cadence>
                 from: take-in-accounts   until: fix-map
handoffs:
  take-in-number -> fix-carve-rule [target-and-segments]: the target,
    the segments it covers, and the date the map is due
  take-in-number -> take-in-accounts [segment-definitions]: the same
    segment definitions, so the account base is pulled on the boundaries
    the map will use
  fix-carve-rule -> draw-candidates [carve-rule]: what a territory is
    cut on, written down, and the account fields that rule reads
  take-in-accounts -> clean-accounts [account-base]: every account with
    the fields the rule needs, and the version each field was read at
  take-in-accounts -> read-coverage [accounts-for-coverage]: the same
    account base, so coverage is read against the accounts actually
    being carved
  clean-accounts -> size-accounts [clean-account-base]: one record per
    real account, with every account the rule cannot read listed by name
  size-accounts -> draw-candidates [account-sizes]: current spend and
    carrying size per account, each figure naming the system it came
    from
  read-coverage -> draw-candidates [last-period-coverage]: which patches
    were worked, which were not, and every account nobody called
  draw-candidates -> model-carrying [candidate-maps]: the candidate
    maps, each placing every account exactly once
  model-carrying -> test-history [carrying-numbers]: what each patch
    carries, with the assumption beside every number
  test-history -> check-balance [backtest-result]: the modelled numbers
    set beside what closed, and every patch the model got wrong by more
    than <percent>
  check-balance -> cost-cuts [balance-findings]: the balance finding per
    patch, with the rule behind every failure
  cost-cuts -> choose-cut [cut-costs]: what each map costs to staff and
    to work, and what it would displace
  choose-cut -> fix-map [chosen-map]: the chosen map, who chose it, and
    why
  fix-map -> record-assumptions [fixed-map]: the map at a version, with
    the rule it was drawn on and the date it takes effect
  record-assumptions -> hand-over-map [model-assumptions]: the
    assumption under every carrying number, and what would make it wrong
deviations:
  clean-accounts -> take-in-accounts [field-the-rule-reads-is-missing]:
    accounts are missing a field the rule cuts on, so the account base
    is taken in again and what stays unreadable is placed by hand
  test-history -> model-carrying [model-fails-history]: the model does
    not reproduce what those patches actually closed, so the carrying
    model is rebuilt rather than the history adjusted
  check-balance -> draw-candidates [patch-nobody-could-work]: a patch
    comes out too big, too spread or too rich for one seller, so the
    candidates are drawn again
  choose-cut -> draw-candidates [no-cut-is-workable]: every map on the
    table fails balance or cost, so the candidates are drawn again and
    the leaders are told which constraint has to move
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for the leader who chooses the map,
           the finance partner and the data steward>
  systems: <your account record> (read), the CRM (read),
           the territory map (write), the model store (write),
           the reporting warehouse (read), the coverage record (write)
  data:    the target for the period, <your segment definitions> at a
           version, the account base at a version, the last <periods>
           of closed revenue, <your cost model>
policy:
  every account sits in exactly one territory. An account in none is a
    defect, and the map does not publish with one
  what a territory is cut on is decided before any map is drawn, and a
    map drawn on a different rule is redrawn rather than argued about
  a carrying number that cannot name the data it came from is marked
    unsourced, and the map carries that mark where a reader sees it
  the map is chosen by a named person. It is never the average of the
    candidates and never the one the model scored highest
  a patch nobody has the capacity to work is named as a gap. Raising
    its number instead is the failure this process exists to prevent
  the maps that were not chosen are kept, each with the reason it lost
measures:
  cycle time: <weeks> from the number to the fixed map
  coverage: <target> share of accounts placed in a workable patch
  accuracy: each patch's modelled carrying number against what it closed
  quality gate: no map is fixed while an account is unplaced, in two
                patches, or carrying an unsourced number
```

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: model the territories        id: <team>/model-the-territories   v1
from: ref/rev/model-the-territories v1
owner: <who>                          effective: <date>
trigger: the carve for <period> opens on <your planning calendar>
         watch: record=<the carve for the period>
                system=<your planning calendar>
                change=<the carve opens for the period>
concurrency: one run per period per market - a re-cut inside the period
             is a new version of the same run, not a new run
goal: every account in exactly one territory, every territory modelled
      for what it can carry, and one map fixed at a version before any
      quota is set against it
phases:
  take-in-number     - human: the target for the period, the segments it
                       covers, and the date the map has to be fixed
                       owner: territory-modeler   after: trigger
                       automation: assisted
  fix-carve-rule     - convenes decide-and-announce: what a territory is
                       cut on, whether that is geography, industry, size
                       or named accounts, decided once and written down
                       before anything is drawn
                       owner: <your revenue operations role>
                       after: take-in-number      automation: never
  take-in-accounts   - runs collect-and-report: every account the carve
                       will place, with the fields the rule reads,
                       pulled at one version of <your account record>
                       owner: analytics           after: take-in-number
                       by: <days>                 automation: autonomous
  clean-accounts     - human: duplicates merged into one account, and
                       every account whose fields the rule cannot read
                       listed by name rather than filled in by guess
                       owner: <your data steward role>
                       after: take-in-accounts
                       by: <days>                 automation: assisted
  size-accounts      - runs assessment: what each account buys today and
                       what it could carry, each figure naming the
                       system it was read from
                       owner: account-monitor     after: clean-accounts
                       by: <days>                 automation: supervised
  read-coverage      - runs collect-and-report: which patches were
                       worked last period, which were never called, and
                       what was left with no owner at all
                       owner: coverage-check
                       after: take-in-accounts    automation: autonomous
  draw-candidates    - runs build-by-talent: <how many> maps drawn on
                       the agreed rule, each one placing every account
                       exactly once
                       owner: territory-modeler
                       after: fix-carve-rule + size-accounts +
                       read-coverage
                       by: <days>                 automation: supervised
  model-carrying     - runs build-by-talent: what each patch on each map
                       can produce in the period, with the assumption
                       written beside every number
                       owner: territory-modeler   after: draw-candidates
                       by: <days>                 automation: supervised
  test-history       - runs assessment: the model run backwards over the
                       last <periods> and set beside what those patches
                       actually closed
                       owner: statistician        after: model-carrying
                       automation: supervised
  check-balance      - runs assessment: no patch above <accounts>
                       accounts or above <amount>, none below <amount>,
                       and no account sitting in two patches
                       owner: coverage-check      after: test-history
                       automation: autonomous
  cost-cuts          - runs allocate-and-reconcile: the sellers, the
                       travel and the support each map needs, priced
                       against <your cost model>
                       owner: capacity-manager    after: check-balance
                       by: <days>                 automation: supervised
  choose-cut         - convenes decide-and-announce: <who> picks one map
                       and says why. The maps not chosen are kept with
                       the reason each one lost
                       owner: <your sales leadership role>
                       after: cost-cuts           automation: never
  fix-map            - human: the chosen map at a version, with the rule
                       it was drawn on and the date it takes effect
                       owner: territory-modeler   after: choose-cut
                       by: <days>                 automation: assisted
  record-assumptions - human: the assumption under every carrying
                       number, and what would make it wrong
                       owner: territory-modeler   after: fix-map
                       automation: assisted
  hand-over-map      - human: the map, its rules and its carrying
                       numbers handed to <your quota process>
                       owner: quota-setter
                       after: record-assumptions  automation: assisted
run-scoped:
  data-quality - runs roll-call                 owner: analytics
                 every: <cadence>
                 from: take-in-accounts   until: fix-map
handoffs:
  take-in-number -> fix-carve-rule [target-and-segments]: the target,
    the segments it covers, and the date the map is due
  take-in-number -> take-in-accounts [segment-definitions]: the same
    segment definitions, so the account base is pulled on the boundaries
    the map will use
  fix-carve-rule -> draw-candidates [carve-rule]: what a territory is
    cut on, written down, and the account fields that rule reads
  take-in-accounts -> clean-accounts [account-base]: every account with
    the fields the rule needs, and the version each field was read at
  take-in-accounts -> read-coverage [accounts-for-coverage]: the same
    account base, so coverage is read against the accounts actually
    being carved
  clean-accounts -> size-accounts [clean-account-base]: one record per
    real account, with every account the rule cannot read listed by name
  size-accounts -> draw-candidates [account-sizes]: current spend and
    carrying size per account, each figure naming the system it came
    from
  read-coverage -> draw-candidates [last-period-coverage]: which patches
    were worked, which were not, and every account nobody called
  draw-candidates -> model-carrying [candidate-maps]: the candidate
    maps, each placing every account exactly once
  model-carrying -> test-history [carrying-numbers]: what each patch
    carries, with the assumption beside every number
  test-history -> check-balance [backtest-result]: the modelled numbers
    set beside what closed, and every patch the model got wrong by more
    than <percent>
  check-balance -> cost-cuts [balance-findings]: the balance finding per
    patch, with the rule behind every failure
  cost-cuts -> choose-cut [cut-costs]: what each map costs to staff and
    to work, and what it would displace
  choose-cut -> fix-map [chosen-map]: the chosen map, who chose it, and
    why
  fix-map -> record-assumptions [fixed-map]: the map at a version, with
    the rule it was drawn on and the date it takes effect
  record-assumptions -> hand-over-map [model-assumptions]: the
    assumption under every carrying number, and what would make it wrong
deviations:
  clean-accounts -> take-in-accounts [field-the-rule-reads-is-missing]:
    accounts are missing a field the rule cuts on, so the account base
    is taken in again and what stays unreadable is placed by hand
  test-history -> model-carrying [model-fails-history]: the model does
    not reproduce what those patches actually closed, so the carrying
    model is rebuilt rather than the history adjusted
  check-balance -> draw-candidates [patch-nobody-could-work]: a patch
    comes out too big, too spread or too rich for one seller, so the
    candidates are drawn again
  choose-cut -> draw-candidates [no-cut-is-workable]: every map on the
    table fails balance or cost, so the candidates are drawn again and
    the leaders are told which constraint has to move
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for the leader who chooses the map,
           the finance partner and the data steward>
  systems: <your account record> (read), the CRM (read),
           the territory map (write), the model store (write),
           the reporting warehouse (read), the coverage record (write)
  data:    the target for the period, <your segment definitions> at a
           version, the account base at a version, the last <periods>
           of closed revenue, <your cost model>
policy:
  every account sits in exactly one territory. An account in none is a
    defect, and the map does not publish with one
  what a territory is cut on is decided before any map is drawn, and a
    map drawn on a different rule is redrawn rather than argued about
  a carrying number that cannot name the data it came from is marked
    unsourced, and the map carries that mark where a reader sees it
  the map is chosen by a named person. It is never the average of the
    candidates and never the one the model scored highest
  a patch nobody has the capacity to work is named as a gap. Raising
    its number instead is the failure this process exists to prevent
  the maps that were not chosen are kept, each with the reason it lost
measures:
  cycle time: <weeks> from the number to the fixed map
  coverage: <target> share of accounts placed in a workable patch
  accuracy: each patch's modelled carrying number against what it closed
  quality gate: no map is fixed while an account is unplaced, in two
                patches, or carrying an unsourced number
```

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: model the territories        id: <team>/model-the-territories   v1
from: ref/rev/model-the-territories v1
owner: <who>                          effective: <date>
trigger: the carve for <period> opens on <your planning calendar>
         watch: record=<the carve for the period>
                system=<your planning calendar>
                change=<the carve opens for the period>
concurrency: one run per period per market - a re-cut inside the period
             is a new version of the same run, not a new run
goal: every account in exactly one territory, every territory modelled
      for what it can carry, and one map fixed at a version before any
      quota is set against it
phases:
  take-in-number     - human: the target for the period, the segments it
                       covers, and the date the map has to be fixed
                       owner: territory-modeler   after: trigger
                       automation: assisted
  fix-carve-rule     - convenes decide-and-announce: what a territory is
                       cut on, whether that is geography, industry, size
                       or named accounts, decided once and written down
                       before anything is drawn
                       owner: <your revenue operations role>
                       after: take-in-number      automation: never
  take-in-accounts   - runs collect-and-report: every account the carve
                       will place, with the fields the rule reads,
                       pulled at one version of <your account record>
                       owner: analytics           after: take-in-number
                       by: <days>                 automation: autonomous
  clean-accounts     - human: duplicates merged into one account, and
                       every account whose fields the rule cannot read
                       listed by name rather than filled in by guess
                       owner: <your data steward role>
                       after: take-in-accounts
                       by: <days>                 automation: assisted
  size-accounts      - runs assessment: what each account buys today and
                       what it could carry, each figure naming the
                       system it was read from
                       owner: account-monitor     after: clean-accounts
                       by: <days>                 automation: supervised
  read-coverage      - runs collect-and-report: which patches were
                       worked last period, which were never called, and
                       what was left with no owner at all
                       owner: coverage-check
                       after: take-in-accounts    automation: autonomous
  draw-candidates    - runs build-by-talent: <how many> maps drawn on
                       the agreed rule, each one placing every account
                       exactly once
                       owner: territory-modeler
                       after: fix-carve-rule + size-accounts +
                       read-coverage
                       by: <days>                 automation: supervised
  model-carrying     - runs build-by-talent: what each patch on each map
                       can produce in the period, with the assumption
                       written beside every number
                       owner: territory-modeler   after: draw-candidates
                       by: <days>                 automation: supervised
  test-history       - runs assessment: the model run backwards over the
                       last <periods> and set beside what those patches
                       actually closed
                       owner: statistician        after: model-carrying
                       automation: supervised
  check-balance      - runs assessment: no patch above <accounts>
                       accounts or above <amount>, none below <amount>,
                       and no account sitting in two patches
                       owner: coverage-check      after: test-history
                       automation: autonomous
  cost-cuts          - runs allocate-and-reconcile: the sellers, the
                       travel and the support each map needs, priced
                       against <your cost model>
                       owner: capacity-manager    after: check-balance
                       by: <days>                 automation: supervised
  choose-cut         - convenes decide-and-announce: <who> picks one map
                       and says why. The maps not chosen are kept with
                       the reason each one lost
                       owner: <your sales leadership role>
                       after: cost-cuts           automation: never
  fix-map            - human: the chosen map at a version, with the rule
                       it was drawn on and the date it takes effect
                       owner: territory-modeler   after: choose-cut
                       by: <days>                 automation: assisted
  record-assumptions - human: the assumption under every carrying
                       number, and what would make it wrong
                       owner: territory-modeler   after: fix-map
                       automation: assisted
  hand-over-map      - human: the map, its rules and its carrying
                       numbers handed to <your quota process>
                       owner: quota-setter
                       after: record-assumptions  automation: assisted
run-scoped:
  data-quality - runs roll-call                 owner: analytics
                 every: <cadence>
                 from: take-in-accounts   until: fix-map
handoffs:
  take-in-number -> fix-carve-rule [target-and-segments]: the target,
    the segments it covers, and the date the map is due
  take-in-number -> take-in-accounts [segment-definitions]: the same
    segment definitions, so the account base is pulled on the boundaries
    the map will use
  fix-carve-rule -> draw-candidates [carve-rule]: what a territory is
    cut on, written down, and the account fields that rule reads
  take-in-accounts -> clean-accounts [account-base]: every account with
    the fields the rule needs, and the version each field was read at
  take-in-accounts -> read-coverage [accounts-for-coverage]: the same
    account base, so coverage is read against the accounts actually
    being carved
  clean-accounts -> size-accounts [clean-account-base]: one record per
    real account, with every account the rule cannot read listed by name
  size-accounts -> draw-candidates [account-sizes]: current spend and
    carrying size per account, each figure naming the system it came
    from
  read-coverage -> draw-candidates [last-period-coverage]: which patches
    were worked, which were not, and every account nobody called
  draw-candidates -> model-carrying [candidate-maps]: the candidate
    maps, each placing every account exactly once
  model-carrying -> test-history [carrying-numbers]: what each patch
    carries, with the assumption beside every number
  test-history -> check-balance [backtest-result]: the modelled numbers
    set beside what closed, and every patch the model got wrong by more
    than <percent>
  check-balance -> cost-cuts [balance-findings]: the balance finding per
    patch, with the rule behind every failure
  cost-cuts -> choose-cut [cut-costs]: what each map costs to staff and
    to work, and what it would displace
  choose-cut -> fix-map [chosen-map]: the chosen map, who chose it, and
    why
  fix-map -> record-assumptions [fixed-map]: the map at a version, with
    the rule it was drawn on and the date it takes effect
  record-assumptions -> hand-over-map [model-assumptions]: the
    assumption under every carrying number, and what would make it wrong
deviations:
  clean-accounts -> take-in-accounts [field-the-rule-reads-is-missing]:
    accounts are missing a field the rule cuts on, so the account base
    is taken in again and what stays unreadable is placed by hand
  test-history -> model-carrying [model-fails-history]: the model does
    not reproduce what those patches actually closed, so the carrying
    model is rebuilt rather than the history adjusted
  check-balance -> draw-candidates [patch-nobody-could-work]: a patch
    comes out too big, too spread or too rich for one seller, so the
    candidates are drawn again
  choose-cut -> draw-candidates [no-cut-is-workable]: every map on the
    table fails balance or cost, so the candidates are drawn again and
    the leaders are told which constraint has to move
bindings:
  roster:  <who holds each role - agents claiming the abstract agents
           above, and named people for the leader who chooses the map,
           the finance partner and the data steward>
  systems: <your account record> (read), the CRM (read),
           the territory map (write), the model store (write),
           the reporting warehouse (read), the coverage record (write)
  data:    the target for the period, <your segment definitions> at a
           version, the account base at a version, the last <periods>
           of closed revenue, <your cost model>
policy:
  every account sits in exactly one territory. An account in none is a
    defect, and the map does not publish with one
  what a territory is cut on is decided before any map is drawn, and a
    map drawn on a different rule is redrawn rather than argued about
  a carrying number that cannot name the data it came from is marked
    unsourced, and the map carries that mark where a reader sees it
  the map is chosen by a named person. It is never the average of the
    candidates and never the one the model scored highest
  a patch nobody has the capacity to work is named as a gap. Raising
    its number instead is the failure this process exists to prevent
  the maps that were not chosen are kept, each with the reason it lost
measures:
  cycle time: <weeks> from the number to the fixed map
  coverage: <target> share of accounts placed in a workable patch
  accuracy: each patch's modelled carrying number against what it closed
  quality gate: no map is fixed while an account is unplaced, in two
                patches, or carrying an unsourced number
```