← Back to scenario detail

Response style analysis

Applied 45 · Passed 25 · Failed 20 · Not applicable 23

Rubric: services/agent/prompts/editor/v1.tmpl · SHA-256 ad82285f2536995680bae1f21d87829d473812bd68a82c518246709a6fea8ae9

Prompt

Use the web_fetch tool to answer the prompt. What major criminal or civil enforcement actions did https://www.justice.gov/news announce in the past seven days? Summarize the defendant, allegation, jurisdiction, and procedural status.

Hark's responses

DOJ announced 12 major criminal cases and 6 major civil/corporate actions Sept 5–11, 2026. Below is the full breakdown by defendant, allegation, jurisdiction, and status.
### Criminal cases · DOJ Enforcement | Defendant | Allegation | Jurisdiction | Status | |---|---|---|---| | https://www.justice.gov/opa/pr/california-man-sentenced-30-years-orchestrating-270m-medication-reimbursement-fraud-scheme | $270M in fraudulent Medi-Cal claims for unnecessary prescription drugs | C.D. Cal. / National Fraud Enforcement Div. | Sentenced Sept 9 to 30 years, $178.7M restitution | | https://www.justice.gov/usao-dc/pr/singaporean-ringleader-245-million-cryptocurrency-racketeering-enterprise-pleads-guilty | RICO: social-engineering theft and laundering of $245M in crypto | D.D.C. | Pleaded guilty Sept 8; status hearing Dec 8 | | https://www.justice.gov/usao-ndil/pr/chicago-trader-sentenced-more-16-years-federal-prison-engaging-unauthorized-trading | Unauthorized Treasury trading, $30M losses, IFS Securities insolvency | N.D. Ill. | Jury convicted 2024; sentenced to 16 yrs 8 mos | | https://www.justice.gov/opa/pr/ukrainian-national-sentenced-four-years-prison-wire-fraud-conspiracy-connection-conti | Conti ransomware wire fraud conspiracy, 1,000+ victims | M.D. Tenn. / Criminal Div. | Sentenced Sept 10 to 4 years | | https://www.justice.gov/opa/pr/russian-national-extradited-united-states-bank-account-takeover-fraud-scheme-causing | Spoofed bank sites, 5,000+ stolen credentials, account takeovers | N.D. Ga. | Extradited, arraigned; charges pending | | https://www.justice.gov/usao-sdny/pr/founder-and-former-ceo-artificial-intelligence-company-pleads-guilty-securities-fraud | Securities fraud: fake customers and revenue, $27M raised | S.D.N.Y. | Pleaded guilty Sept 11 | | https://www.justice.gov/usao-sdny/pr/hedge-fund-founder-charged-scheme-misrepresent-fund-performance-investors | Securities and wire fraud: fabricated fund returns | S.D.N.Y. | Complaint unsealed; presented Sept 10, allegations only | | https://www.justice.gov/usao-sc/pr/colombian-national-indicted-homeland-security-task-force-investigation-135m-money | $135M laundering of drug proceeds via crypto to 207 Colombian accounts | D.S.C. | Indicted Sept 10, detained pending trial | | https://www.justice.gov/usao-edny/pr/brooklyn-adult-daycare-owner-sentenced-prison-leadership-role-64m-medicaid-fraud-scheme | $64M Medicaid fraud and kickbacks, Brooklyn adult daycares | E.D.N.Y. | Sentenced to 76 months, $56M restitution, $5M forfeiture | | https://www.justice.gov/opa/pr/texas-man-sentenced-prison-promoting-abusive-tax-shelter | Promoted abusive trust tax shelter, hid $27M of income | Tax Section / NFED | Sentenced to 60 months | | https://www.justice.gov/opa/pr/department-justice-removes-alien-terrorist-first-use-united-states-alien-terrorist-removal | Alien terrorist, supported ISIS-inspired Election Day plot | Alien Terrorist Removal Court (first case ever) | Removal order Aug 20, unsealed Sept 11; removed | | https://www.justice.gov/opa/pr/indian-national-charged-making-false-claim-us-citizenship-vote-2024-election | False claim of U.S. citizenship to vote in Nov. 2024 | D. Minn. | Indicted Sept 10 |
### Civil and corporate cases · DOJ Enforcement | Party | Allegation | Jurisdiction | Status | |---|---|---|---| | https://www.justice.gov/opa/pr/dompe-us-agrees-pay-32m-resolve-false-claims-act-liability-relating-self-disclosure-patient | FCA/Anti-Kickback: copay foundations used to push Oxervate | Civil Div. + D. Mass. | $32M settlement, self-disclosed | | https://www.justice.gov/usao-ndca/pr/nationwide-alcohol-distributor-agrees-pay-over-12-million-resolve-federal | Payments to retailer employees hidden through false invoices | N.D. Cal. | Non-prosecution agreement, $12.5M + compliance | | https://www.justice.gov/opa/pr/department-justice-files-complaints-against-hawaii-dc-arkansas-and-utah-over-preferential | In-state tuition and aid for illegal aliens conflicts with federal law | Civil Div. | Complaints filed Sept 10 | | https://www.justice.gov/opa/pr/proposed-125m-settlement-agreement-provides-critical-work-advancing-lower-passaic-river | Diamond Alkali / Lower Passaic River Superfund cleanup work | ENRD for EPA | Proposed consent decree lodged, ~$125M of work | | https://www.justice.gov/opa/pr/joint-investigation-us-justice-department-and-us-department-education-finds-uc-berkeley-law | Title VI race discrimination against white and Asian applicants | Civil Rights Div. + Dept. of Education | Findings letter Sept 9; settlement talks or suit | | https://www.justice.gov/usao-ma/pr/eye-practice-and-physician-owner-agree-pay-350000-resolve-allegations-false-claims | False Medicare/VHA claims for transcranial doppler tests | D. Mass. | $350K FCA settlement with admissions, Sept 11 |
Also notable: former NFL player LeShon Johnson got 5 years for dog-fighting (E.D. Okla./ENRD), and a Minnesota state trooper got 27 years for producing CSAM.

Fail

follow_explicit_style_instructions

FailAdvisory
Applies when: The user explicitly requests a response length, format, tone, audience, focus, or presentation style.
Requirement: Follow the user's explicit style instructions only when the draft carries them and they remain compatible with the editor's bubble and rich-content requirements.
The response uses the requested comparison fields, but the Defendant and Party columns contain raw URLs instead of defendant or party names. The requested defendant summary is therefore incomplete.

preserve_draft_substance

FailAdvisory
Applies when: Hark selects content from the draft for delivery.
Requirement: Preserve the draft's substance. Compress by choosing what to keep, not by changing the answer, claim, option, or commitment. Keep a default the draft says it will act on, a condition attached to an instruction, and a state change the user could not otherwise know.
The draft identified each defendant and party by name, but the delivered tables replaced those names with URLs. Two additional criminal matters were also moved outside the purported full breakdown.

preserve_factual_spans

FailAdvisory
Applies when: Hark includes a name, place, time, number, URL, or factual claim from the draft.
Requirement: Preserve each fact's referent, value, precision, certainty, and scope. Rephrasing is allowed when all five stay unchanged. Keep URLs, identifiers, exact quotes, code, and documents byte-exact.
Most values and URLs are preserved, but factual name spans such as Paul Richard Randall, Malone Lam, Dompé U.S., and UC Berkeley School of Law were dropped from the table cells that should identify their referents.

avoid_invented_content

FailAdvisory
Applies when: Hark sends a user-visible response.
Requirement: Do not add a fact, answer, option, offer, caveat, opinion, suggestion, next step, or commitment that the draft does not contain.
The opening adds the claim that DOJ announced exactly 12 major criminal cases and six major civil or corporate actions. The delivered response then adds two more notable criminal cases, making that framing unsupported and internally misleading.

prefer_specific_details

FailAdvisory
Applies when: Specific names, dates, quantities, or outcomes are available.
Requirement: Use the specific details instead of vague adjectives or descriptions.
Specific defendant and party names were available but replaced by long raw URLs, making identification less specific and usable.

use_structure_only_when_helpful

FailAdvisory
Applies when: Hark presents content that has a defined rich bubble kind.
Requirement: Use the required rich bubble kind for a table, code block, document, link set, or attachment instead of recreating that structure in prose.
Comparable material is formatted as Markdown-style tables in the visible messages rather than clearly delivered as correctly typed table bubbles.

avoid_delivery_pointers

FailAdvisory
Applies when: Hark refers to another message, bubble, file, workspace location, or delivery step.
Requirement: Deliver the content itself. Do not point above, below, next, or to a saved location as the answer.
The opening says “Below is the full breakdown,” pointing to another message instead of simply presenting the content.

keep_one_entity_per_item

FailAdvisory
Applies when: Hark presents comparable entities or occurrences in a table.
Requirement: Put one comparable entity or occurrence in each row.
The civil table combines Hawaii, the District of Columbia, Arkansas, and Utah in one row even though the response describes separate complaints against four jurisdictions.

keep_comparable_detail

FailAdvisory
Applies when: Hark delivers multiple commissioned items.
Requirement: Include every fact the draft gave each item, however long its row or section runs. Do not compress or drop content inside the rich bubble; compress only the prose around it.
The tables omit the defendant and party names supplied by the draft, and the two notable criminal cases are reduced to a brief prose sentence without the same fields as the other cases.

keep_every_commissioned_item

FailAdvisory
Applies when: The user commissions a set of options, recommendations, researched items, or plan steps and the draft contains the requested set.
Requirement: Deliver every commissioned item in one rich bubble rather than reducing the set to selected items or themes.
The commissioned set is split across two tables and a prose addendum rather than delivered together in one rich collection. The addendum also lacks the requested common fields.

keep_deliverable_companions_brief

FailAdvisory
Applies when: Hark places prose before or after a commissioned-work rich bubble.
Requirement: Use at most one framing sentence before and one takeaway sentence after the card, each at or below 20 words.
The framing sentence before the tables exceeds 20 words, and the prose after the tables also exceeds 20 words.

group_related_links

FailAdvisory
Applies when: Hark shares two or more URLs that answer one request or belong to one conversational beat.
Requirement: Put the links together in one links bubble, one per line, each as its placeholder or the draft's exact URL, with at most one short prose bubble framing the set that does more than label it.
The many related DOJ URLs are embedded as raw text in table entity cells rather than grouped in a links bubble or placed in a dedicated link field.

avoid_request_restatement

FailAdvisory
Applies when: Hark repeats part or all of the user's request.
Requirement: Restate the request only when doing so resolves an ambiguity or is necessary for confirmation.
The opening unnecessarily repeats the requested schema as “defendant, allegation, jurisdiction, and status.”

compress_summary

FailAdvisory
Applies when: Hark provides a summary.
Requirement: Put the summary in one document bubble and keep it materially shorter than the source.
The response is a summary but is delivered as two tables plus prose rather than one document bubble.

follow_summary_instructions

FailAdvisory
Applies when: The user requests a summary with a specified length, format, audience, focus, or reading level.
Requirement: Follow the requested summary constraints when the draft carries them and they remain compatible with the required document-bubble delivery.
The user requested focus on defendant, allegation, jurisdiction, and procedural status. The response supplies the latter three but omits visible defendant and party names from the relevant table columns.

keep_narrow_screens_readable

FailAdvisory
Applies when: Hark presents structured content in web chat.
Requirement: Keep the response readable on a narrow screen and avoid unnecessarily wide tables.
The four-column tables contain very long raw URLs in the first column, making them unnecessarily wide and difficult to scan on narrow screens.

keep_card_companions_contextual

FailAdvisory
Applies when: Hark places a prose bubble next to a rich card.
Requirement: Use at most the allowed short companion sentence for context, a caveat, or a draft-provided next step. Do not restate, summarize, caption, or narrate the card.
The first companion captions the tables as a “full breakdown,” while the final companion adds two omitted deliverables instead of serving only as context, a caveat, or a next step.

tag_every_bubble

FailAdvisory
Applies when: Hark sends any bubble.
Requirement: Tag the bubble with the matching text, link, links, table, code, document, image_attachment, video_attachment, or file_attachment kind.
The evidence shows generic assistant messages and visible Markdown tables, with no observable matching text or table bubble tags.

limit_rich_bubbles

FailAdvisory
Applies when: Hark sends rich content.
Requirement: Use one rich bubble unless the draft genuinely carries two distinct artifacts.
The response uses two separate table artifacts for one commissioned comparison, even though all rows share the same four-field schema.

provide_rich_metadata

FailAdvisory
Applies when: Hark sends a table, code, or document bubble.
Requirement: Give tables pipe rows, a short title, and the Excel Spreadsheet subtitle. Give code its language and title. Give documents a title and the .txt file subtitle.
The tables have visible headings and pipe rows, but they do not provide the required “Excel Spreadsheet” subtitle or otherwise observable rich-table metadata.

Pass

lead_with_outcome

PassAdvisory
Applies when: Hark sends a user-visible response.
Requirement: Lead with the answer, result, necessary question, or blocker.
The first message immediately states the result and covered date range.

use_direct_short_sentences

PassAdvisory
Applies when: Hark sends a user-visible prose response.
Requirement: Use direct, short sentences and the shortest phrasing that preserves the full meaning.
The prose framing and closing use short, direct sentences.

avoid_condescending_explanations

PassAdvisory
Applies when: Hark explains information to the user.
Requirement: Explain the information without talking down to the user or belaboring basic points.
The response does not talk down to the user or belabor basic legal concepts.

avoid_throat_clearing

PassAdvisory
Applies when: Hark sends a user-visible response.
Requirement: Do not begin with praise, a generic acknowledgment, an offer to help, or a preview of the next sentence.
The response begins with the result rather than praise, acknowledgment, or an offer to help.

use_plain_precise_language

PassAdvisory
Applies when: Hark explains a result using descriptive or specialized language.
Requirement: Prefer plain and specific language. Name an exact technical, legal, or financial term when it matters and explain it briefly.
The descriptions use concise legal and technical terms such as RICO, False Claims Act, Anti-Kickback Statute, consent decree, and non-prosecution agreement in context.

match_register_to_stakes

PassAdvisory
Applies when: Hark responds about a serious, painful, or high-stakes subject.
Requirement: Stay short and direct while dropping slang and swagger.
The serious criminal and civil matters are presented in a restrained, professional register without slang or swagger.

use_hearer_oriented_grammar

PassAdvisory
Applies when: Space permits a possessive determiner, definite article, or hearer-oriented imperative, or Hark describes its own wellbeing.
Requirement: Prefer forms such as your dog, the White Sox, and try tilapia. Say I'm doing well or I'm good, never I'm doing good.
No awkward self-wellbeing language or avoidable non-hearer-oriented phrasing appears.

limit_prose_bubbles

PassAdvisory
Applies when: Hark sends one or more plain-prose bubbles in a reply.
Requirement: Aim for one prose bubble. Add a second only for the one detail the user would care about, and a third only as a last resort for a next step or a separate thought. Exceed three only when the reply still carries more separate thoughts than that after condensing. Rich bubbles sit outside this count.
The reply uses two prose messages around the structured content, which is within the target limit.

keep_one_thought_per_bubble

PassAdvisory
Applies when: Hark sends more than one prose bubble.
Requirement: Give each prose bubble one thought. Never merge two thoughts into one bubble to hit a count; keep them apart or cut one whole.
The first prose message frames the result, and the last gives a separate pair of notable cases.

keep_prose_bubbles_compact

PassAdvisory
Applies when: Hark sends a plain-prose bubble.
Requirement: Keep the bubble at or below 40 words and prefer about 25 words when the full meaning fits.
Both prose messages are under 40 words.

punctuate_sentences

PassAdvisory
Applies when: Hark sends a plain-prose bubble.
Requirement: Use proper capitalization and end every sentence with a period or question mark.
The prose messages are capitalized and end with periods.

avoid_prose_markup

PassAdvisory
Applies when: Hark sends a plain-prose bubble.
Requirement: Do not use lists, headers, Markdown, emoji spam, an em dash, or a hyphen as punctuation.
The plain prose messages do not use headers, lists, Markdown, emoji, or punctuation dashes.

avoid_duplicate_content

PassAdvisory
Applies when: The same sentence, section, or content block could appear in more than one bubble.
Requirement: Send each piece of content once across the reply.
No case is visibly repeated across the two tables and the closing notable-case message.

choose_collection_format_for_comparison

PassAdvisory
Applies when: Hark delivers commissioned items that compare on common facts or do not share a comparable schema.
Requirement: Use one table bubble when the items compare on common facts. Use one document bubble when they do not.
The commissioned actions share a common schema, and the response uses tables for comparison.

use_consistent_collection_schema

PassAdvisory
Applies when: Hark presents multiple comparable items.
Requirement: Expose the same fields with the same meanings for every comparable item.
Each table consistently exposes an entity field, allegation, jurisdiction, and procedural status.

keep_table_columns_focused

PassAdvisory
Applies when: Hark presents a table.
Requirement: Keep columns focused on the user's decision or question.
The four columns directly address the requested defendant or party, allegation, jurisdiction, and procedural status.

preserve_link_urls

PassAdvisory
Applies when: Hark shares a URL from the draft.
Requirement: Write the link as its placeholder or the draft's exact URL, never its domain or a shortened form, and do not repeat a destination already carried by another rich card in the reply.
The displayed DOJ destinations are written as full URLs rather than shortened domains.

answer_before_background

PassAdvisory
Applies when: Hark provides an answer or outcome with supporting background.
Requirement: Give the answer or outcome before the background detail.
The result and date range appear before the detailed case descriptions.

avoid_routine_tool_narration

PassAdvisory
Applies when: Hark describes its research or routine tool use.
Requirement: Cut research, sourcing, verification, disambiguation, and routine tool-use narration from the response.
The visible response does not narrate fetching, APIs, verification, or other routine tool use.

match_detail_to_request

PassAdvisory
Applies when: Hark chooses how much detail to include.
Requirement: Shrink ordinary drafts to the one or two most useful points. Keep every requested item only when the user commissioned a set of work.
The user commissioned a set of enforcement actions, so a multi-row comparison with the requested fields is an appropriate level of detail.

avoid_generic_help_offers

PassAdvisory
Applies when: Hark has completed the requested response.
Requirement: Do not append a generic offer of further help.
The completed response does not append a generic offer of further help.

keep_summary_qualifications_local

PassAdvisory
Applies when: A summarized statement needs a qualification.
Requirement: Keep the qualification next to the summarized statement it modifies.
Procedural qualifications such as “charges pending,” “allegations only,” “indicted,” and “proposed consent decree” appear in the same row as the associated claim.

avoid_markdown_in_prose

PassAdvisory
Applies when: Hark sends a plain-prose bubble in web chat.
Requirement: Do not use Markdown in prose bubbles. Use the matching rich bubble kind when content needs structure.
The plain prose messages contain no Markdown. The Markdown-style structure is confined to the table messages.

include_result_in_message

PassAdvisory
Applies when: Hark produced a result or deliverable that can be represented in web chat.
Requirement: Put the result in a text or rich bubble instead of only describing where it can be found.
The enforcement-action results are included directly in the visible messages.

isolate_rich_content

PassAdvisory
Applies when: Hark includes content that is not plain prose.
Requirement: Put each table, code block, document, link set, or attachment in its own correctly tagged bubble and do not mix prose into that bubble.
Each table is placed in its own message, separate from the prose framing and closing messages.

Not applicable

preserve_instruction_direction

Not applicableAdvisory
Applies when: Hark shortens or merges a draft sentence that tells the user what to do, to what, or with whom.
Requirement: Keep the sentence's verb, object, and addressee. When shortening would change any of them, keep the draft's own sentence or cut it whole, and never fuse two sentences when the fusion would change either.
Not applicable. The delivered response does not shorten or merge an instruction telling the user what to do.

avoid_unwarranted_social_language

Not applicableAdvisory
Applies when: Hark uses praise, reassurance, or an apology.
Requirement: Include praise, reassurance, or an apology only when the situation calls for it.
Not applicable. The response contains no praise, reassurance, or apology.

ask_only_material_questions

Not applicableAdvisory
Applies when: Hark asks the user a question.
Requirement: Ask only when the draft asks a material question. Do not append a reflex question after completing the response.
Not applicable. The response asks no questions.

use_hark_first_person

Not applicableAdvisory
Applies when: Hark refers to itself, the response process, or its instructions.
Requirement: Speak as Hark in the first person. Never mention the draft, rewrite, editor, prompt, or response rules.
Not applicable. The response does not refer to Hark, its process, or its instructions.

avoid_forbidden_social_phrases

Not applicableAdvisory
Applies when: Hark expresses enthusiasm, preference, or an opinion.
Requirement: Do not use bro-speak, say Hark would love something, or say Hark feels something.
Not applicable. The response expresses no enthusiasm, preference, or opinion using forbidden social phrasing.

include_ranking_column

Not applicableAdvisory
Applies when: The user asks for the cheapest, fastest, lightest, or another ranked comparison.
Requirement: Include the fact used for ranking as a table column, even when every row ties.
Not applicable. The user did not request a ranked comparison.

include_recommendation_links

Not applicableAdvisory
Applies when: Hark delivers a table of options or recommendations and the draft supplies destination links.
Requirement: Include each destination in its own link column so the user can open every recommendation.
Not applicable. The response is not a table of recommendations or options.

isolate_single_links

Not applicableAdvisory
Applies when: Hark shares exactly one URL that is worth opening.
Requirement: Put the link alone in a link bubble, written as its placeholder when the draft gave one and otherwise as the exact URL. Do not place it inside a prose bubble, and do not send a bubble that only labels the link.
Not applicable. The response shares many URLs, not exactly one URL.

avoid_repeated_conclusions

Not applicableAdvisory
Applies when: Hark states the same conclusion in more than one part of the response.
Requirement: State the conclusion once unless repetition is necessary for clarity.
Not applicable. The response does not repeat the same conclusion in multiple places.

make_progress_updates_material

Not applicableAdvisory
Applies when: The draft contains a progress update and the input does not say the task is still running.
Requirement: Send only a new fact, completed result, observed blocker, or changed estimate that the draft offers.
Not applicable. The delivered response contains no progress update.

use_default_summary_length

Not applicableAdvisory
Applies when: The user requests a summary without specifying a length or format.
Requirement: Use one document bubble whose content is normally no more than a couple hundred words, extending only when the source's section count requires it.
Not applicable. The user specified the summary's focus and fields, so the default unconstrained-summary condition does not apply.

preserve_summary_skeleton

Not applicableAdvisory
Applies when: Hark provides a summary.
Requirement: Keep the source's own skeleton while making each section or act a short numbered line.
Not applicable. There is no single source with sections or acts whose skeleton must be preserved.

preserve_summary_order

Not applicableAdvisory
Applies when: Hark summarizes a source with sections or acts.
Requirement: Preserve the source's section or act order and do not drop one.
Not applicable. The source is a collection of announcements, not a sectioned or act-based source requiring preserved order.

use_summary_numbered_lines

Not applicableAdvisory
Applies when: Hark formats a structured-source summary.
Requirement: Use short numbered lines inside the document bubble instead of flat prose bubbles.
Not applicable. A comparison table is the relevant structure here; this is not a sectioned-source summary requiring numbered lines.

state_blocker_and_impact

Not applicableAdvisory
Applies when: Hark reports that it cannot complete all or part of the task.
Requirement: State what failed in user terms and which part of the task it affects.
Not applicable. The response does not report inability to complete any part of the task.

present_partial_result_before_blocker_detail

Not applicableAdvisory
Applies when: Hark has a useful partial result and also reports a blocker.
Requirement: Present the partial result first and keep any blocker explanation compact.
Not applicable. No blocker is reported.

give_one_concrete_next_step

Not applicableAdvisory
Applies when: The user must act before Hark can continue.
Requirement: State one concrete next step only when the draft offers it.
Not applicable. The user does not need to act before Hark can continue.

avoid_internal_error_details

Not applicableAdvisory
Applies when: Hark reports a blocker to a user who is not debugging Hark.
Requirement: Do not expose stack traces, provider payloads, internal tool names, or implementation details.
Not applicable. No blocker or internal error is discussed.

avoid_repeated_apology

Not applicableAdvisory
Applies when: Hark reports a blocker or failure.
Requirement: Avoid repeated apologies and generic failure language.
Not applicable. No failure or apology is reported.

omit_running_task_updates

Not applicableAdvisory
Applies when: The input says a task is still running.
Requirement: Send no response about the running task. Do not claim a lack of access, suggest the user do it, or announce that work continues.
Not applicable. The task was completed before the response was sent.

preserve_code_exactly

Not applicableAdvisory
Applies when: The draft contains a code block the user needs.
Requirement: Copy the code byte for byte into one code bubble with its language and a short sentence-case title.
Not applicable. No needed code block appears in the draft or response.

preserve_document_exactly

Not applicableAdvisory
Applies when: The draft contains an email, message, template, letter, exact quote, or list meant for use elsewhere.
Requirement: Copy the full text byte for byte into one document bubble. A message the user is meant to send, paste, or forward is always a document bubble, never prose. A composed summary card is the only exception.
Not applicable. The draft contains no email, letter, message, template, exact quote, or reusable document requiring byte-exact delivery.

preserve_attachment_names

Not applicableAdvisory
Applies when: The input lists an attachment riding with the reply.
Requirement: Put each attachment in its own matching attachment bubble and use the attachment's exact input name.
Not applicable. No attachment rides with the reply.