Audit: QRS - THC for Health & Longevity
Audit conducted on 04/08/2026 00:23 using AI4L / Opus 5
Summary
| Items | Count |
|---|---|
| Total | 91 |
| Passed | 81 |
| Failed | 0 |
| N/A | 10 |
| Pass Rate | 100.00% |
- Total = Passed + Failed + N/A
- Pass Rate = Passed / (Passed + Failed) × 100
- N/A items are excluded from the pass rate calculation
1. General Rules
| # | Description | Result | Comments |
|---|---|---|---|
| 1.1 | Every claim, magnitude, label, recommendation, and statement in the QRS is literally supported by content in the source ER. | 🟢 | All protocol values (0.5–2.5 mg evening, 2.5–20 mg daily, 1–3 h before sleep), time-to-effect values, all 13 biomarker targets, cadence, benefit/risk tier items, contraindications and interactions trace verbatim to ER lines 412–432, 462–472, 515, 537–555, 559–565. |
| 1.2 | Where the ER uses cautious phrasing (“not formally studied”, “None documented in human trials to date”, “theoretical concern”, “data are limited”), the QRS uses the same phrasing. | 🟢 | No hedged ER phrasing is hardened; speculative tiers are carried through as “Speculative” in both Benefits and Risks. |
| 1.3 | The QRS never strengthens an ER claim (e.g., “not formally studied” → “not required”) or softens one (e.g., “do not use during pregnancy” → “use with caution during pregnancy”). | 🟢 | Pregnancy and lactation remain an absolute contraindication; the under-25 regular-use bar and the 160/100 mmHg threshold are preserved at ER strength. |
| 1.4 | The QRS does not relabel an ER fact under a different decision category. A “Benefit-Modifying Factor” from ER section is not surfaced as a “Caution”; a “Risk-Modifying Factor” is not surfaced as a “Side Effect”; etc. | 🟢 | Contraindications come only from the ER’s two “Populations who should avoid THC” bullets; Key Interactions come only from the ER’s nine interaction bullets; no Benefit- or Risk-Modifying Factor is surfaced as a gate. |
| 1.5 | PubMed IDs, study citations, expert names, clinical trial identifiers (NCT*), and brand names appear in the QRS only if they appear in the source ER for the same fact. | 🟢 | The QRS contains no PMIDs, no citations, no NCT identifiers, no author or expert names, and no product brand names. |
| 1.6 | The QRS does not introduce new attributions. | 🟢 | No attributions of any kind are present in the QRS. |
2. Focus, Tone & Audience
| # | Description | Result | Comments |
|---|---|---|---|
| 2.1 | The QRS follows the tone of the ER, which is determined by the ER’s own language, phrasing, and framing. | 🟢 | Measured, evidence-weighted register matches the ER, including its net-sceptical read of THC for longevity. |
| 2.2 | The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging | 🟢 | Quantified targets, tiered benefit/risk lists, and explicit gates enable decision-making without moralising. |
| 2.3 | The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor | 🟢 | Content is stated as findings and thresholds, not as instructions to a patient. |
| 2.4 | The QRS avoids language that implies medical or clinical advice | 🟢 | No imperatives or prescriptions; the protocol cells describe standard protocols rather than directing action. |
| 2.5 | The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising” | 🟢 | All cells are declarative noun phrases and statements of fact. |
| 2.6 | The QRS never addresses “the reader” directly — it presents evidence, not guidance | 🟢 | No second-person pronouns appear anywhere in the QRS body. |
| 2.7 | The QRS is written in plain language, avoiding unnecessary medical jargon | 🟢 | Technical terms retained (New York Heart Association Class III–IV, Child-Pugh Class B or C, CYP3A4) are load-bearing decision qualifiers required by items 8.5 and 9.5; abbreviations are expanded on first use in the Monitoring table. |
| 2.8 | Information is presented in a concise and very compact manner | 🟢 | Benefit and risk tiers are reduced to bare semicolon-separated headings; Monitoring “Why” cells are single clauses. |
| 2.9 | It DOES NOT address the reader directly | 🟢 | Confirmed: no direct address anywhere in the sheet. |
| 2.10 | The target audience is health- and longevity-oriented adults who are risk-aware, proactive, and actively seeking to optimize health or apply the intervention under review. | 🟢 | Monitoring panel (flow-mediated dilation, fasting insulin, hs-CRP, testosterone) and qualitative markers (training output, morning cognitive clarity) are pitched at this audience. |
| 2.11 | The target audience is willing to employ lifestyle and behavioral changes as well as follow protocols that may be inconvenient, costly, or require effort. | 🟢 | Specialist testing (flow-mediated dilation ultrasound, DEXA T-score, 12-lead ECG, semen analysis) is presented without hedging on cost or effort. |
| 2.12 | The document is NOT written for the general population, who are unwilling to employ lifestyle and behavioral changes or follow protocols that may be inconvenient, costly, or require effort. | 🟢 | Functional targets (hs-CRP <0.5 mg/L, fasting insulin 2–5 µIU/mL, resting heart rate 50–65 bpm) sit far tighter than conventional reference ranges. |
| 2.13 | Framing, takeaways, and risk/benefit weighting throughout the document reflect this audience, including where an intervention’s signal for the average person differs from its signal for this audience. | 🟢 | Endothelial impairment, persistent cognitive deficits, and reduced training output are given prominence, matching the ER’s audience-specific reweighting. |
| 2.14 | The document’s own voice frames usage in longevity terms, not “anti-aging” (e.g., “anti-aging clinics”, “anti-aging community”, “anti-aging medicine”). Proper names that contain “anti-aging” (e.g., “American Academy of Anti-Aging Medicine”) are quoted verbatim. | 🟢 | The term “anti-aging” does not appear; the risks list uses “vascular ageing” and “cognitive ageing”. |
| 2.15 | The document’s own voice uses formal clinical and scientific terminology, not colloquial or consumer-grade language (e.g., “oral medication” not “pill(s)”; “injection” not “shot”; “adverse event” not “bad reaction”). Direct quotes from sources are exempt. | 🟢 | Body of the sheet uses clinical register (“oral preparations”, “orthostatic hypotension”, “psychomotor impairment”); the deliberately plain At-A-Glance wording is mandated by item 7.4. |
3. Template Integrity
| # | Description | Result | Comments |
|---|---|---|---|
| 3.1 | The following labels and headings on the QRS are fixed and not modified: Card and section headings: “Protocol”, “Time to effect”, “Benefits”, “Risk & Side Effects”, “Monitoring”, “Qualitative Assessment”; Gate headings: “Contraindications”, “Key Interactions”; Tier labels: “High”, “Medium”, “Low”, “Speculative”; Table column headers in Monitoring: “Marker”, “Target”, “Why” | 🟢 | All fixed headings, gate headings, tier labels, and column headers match the template byte-for-byte. |
| 3.2 | All “…” from the [qrs_template] are present in the the QRS. | 🟢 | All 38 template variable names are present; the repeatable marker_#_* and qualitative_item_# spans are correctly expanded to 13 marker rows and 7 qualitative items. |
| 3.3 | Spans that are not addressed in a checklist item are left unchanged | 🟢 | A normalised structural diff against the template shows zero changes outside the variable spans and the metadata block. |
4. Formatting
| # | Description | Result | Comments |
|---|---|---|---|
| 4.1 | When the source ER section is empty, the QRS uses the ER’s own empty-state phrasing verbatim. Typical phrasings are “None documented in human trials to date” and “Not formally studied” | N/A | No source ER section that feeds the QRS is empty. |
| 4.2 | Where the ER presents a bulleted item as “Label: content”, the QRS uses the ER’s bold label verbatim as the cell or row label. | 🟢 | “Best time of day” and “Single dose versus split dosing” are verbatim ER bold labels; “Standard clinical protocol” is the ER bold label with only its trailing em-dash mnemonic stripped. |
| 4.3 | Labels are not paraphrased, abbreviated, or invented. | 🟢 | Monitoring marker names and qualitative item labels are lifted verbatim from the ER table and list; time-to-effect labels are derived as required by item 11.4 because the ER supplies no per-item bold labels there. |
| 4.4 | The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels. | 🟢 | A codepoint scan returns no emoji or symbol characters anywhere in the file. |
| 4.5 | The QRS is designed to render on one A4 page. Any section that has more content in the ER than fits the per-section budget is condensed by the LLM, not extended onto a second page. | 🟢 | Every section is condensed to its minimum expressible form (bare tier headings, single-clause “Why” cells, trimmed gate items); no section carries ER prose forward unreduced. |
5. Metadata
| # | Description | Result | Comments |
|---|---|---|---|
| 5.1 | The metadata is placed inside a single HTML comment that is the first element after “<!doctype html>” and before any other comment, head, or body content. | 🟢 | The comment opens on line 2, immediately after <!doctype html> on line 1. |
| 5.2 | Inside that HTML comment the YAML block is delimited by a line “—” opening and a line “—” closing. Text before the opening “—” is permitted but is not parsed as YAML. | 🟢 | Opening --- on line 3, closing --- on line 13; the preceding descriptive line is permitted. |
| 5.3 | The metadata is not visible in any rendered view of the QRS and is not surfaced by any other element on the sheet. | 🟢 | It sits wholly inside an HTML comment and is not duplicated in the header, footer, or any span. |
| 5.4 | All frontmatter values are trimmed: no leading or trailing whitespace, no surrounding quotes unless the value contains a colon, bracket, or leading special character that requires YAML quoting. | 🟢 | Only duration: "00:03" is quoted, correctly, because it contains a colon. |
| 5.5 | The filename of the source ER is stated as “er_filename: [er_filename]” | 🟢 | er_filename: thc_2026-0803-1910_Opus_ER.md — matches the source ER’s own filename frontmatter value. |
| 5.6 | Version of the QRS.md file used to create the document is stated as “qrs_prompt_version: [Version of QRS.md]” | 🟢 | qrs_prompt_version: 26.7.02 matches the version badge at the top of QRS.md. |
| 5.7 | Creation date and time of the document is stated as “qrs_creation_date: [YYYY-MMDD-HHMM]” (e.g., 2026-0501-1430) | 🟢 | qrs_creation_date: 2026-0804-0001 conforms to the required format. |
| 5.8 | The nickname of the AI used to create the document is stated as “qrs_creator_ai_nickname: [qrs_creator_ai_nickname]” | 🟢 | qrs_creator_ai_nickname: Opus |
| 5.9 | The nickname of the AI is just a single word model name without version, etc. (e.g., Opus, Sonnet, Grok, Gemini, ChatGPT) | 🟢 | “Opus” is a single word with no version or qualifier. |
| 5.10 | The full name of the AI used to create the document is stated as “qrs_creator_ai_fullname: [qrs_creator_ai_fullname]” | 🟢 | qrs_creator_ai_fullname: Opus 5 |
| 5.11 | The full name of the AI consists of the [qrs_creator_ai_nickname] and the model version number and no additional qualifier (e.g., Opus 4.6, Sonnet 3.2, Grok 4.5, Gemini 3.1, ChatGPT 5.4) | 🟢 | “Opus 5” is nickname plus version number with no trailing qualifier. |
| 5.12 | The filename of the document is stated as “qrs_filename: [filename of this document]” | 🟢 | qrs_filename: thc_2026-0803-1910_Opus_QRS.html matches the file on disk. |
| 5.13 | All frontmatter values are trimmed: no leading or trailing whitespace, no surrounding quotes unless the value contains a colon, bracket, or leading special character that requires YAML quoting. | 🟢 | Re-verified: all nine keys carry trimmed values; quoting is used only where YAML requires it. |
6. Page Title & Header
| # | Description | Result | Comments |
|---|---|---|---|
| 6.1 | [page_title] is set to the [canonical_topic] of the ER frontmatter followed by “ - Quick Reference Sheet” (e.g., “Intervention - Quick Reference Sheet”). The [canonical_topic] is HTML-entity-encoded as needed (e.g., & for &) |
🟢 | THC for Health & Longevity - Quick Reference Sheet, with the ampersand correctly entity-encoded. |
| 6.2 | [header_topic] is set to the [canonical_topic] of the ER frontmatter, with HTML entities encoded as needed (e.g., & for &) |
🟢 | THC for Health & Longevity matches the ER canonical_topic. |
| 6.3 | [header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY] | 🟢 | 08/04/2026, the correct MM/DD/YYYY rendering of 2026-0804. |
| 6.4 | [header_subline_model] is set to [qrs_creator_ai_fullname] | 🟢 | Opus 5, matching the frontmatter value. |
| 6.5 | No additional header content appears: no badge, version stamp, AKA / alternate names line, source-AI attribution, audit date, or QRS variant marker. | 🟢 | The header carries only the title and the template’s standard subline; the ER’s “Also known as” line is not carried over. |
7. At-A-Glance Section
| # | Description | Result | Comments |
|---|---|---|---|
| 7.1 | [at_a_glance] is dense, execution-oriented summary of the ER Conclusion section |
🟢 | Condenses the ER Conclusion’s three paragraphs into narrow established uses, modest conflicted uses, and the harm profile. |
| 7.2 | [at_a_glance] is no longer than 60 words | 🟢 | 51 words by machine count. |
| 7.3 | Every fact in [at_a_glance] is supported by a distinct passage in the ER. | 🟢 | Narrow firm uses and modest pain/stiffness relief map to ER line 595; heart rate, vessel flexibility, judgment, and difficulty stopping map to ER line 597. |
| 7.4 | It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead | 🟢 | No acronyms; “less flexible blood vessels” replaces endothelial function and “difficulty stopping” replaces dependence. |
| 7.5 | It DOES NOT cite specific trials (names, years, sample sizes, p-values) | 🟢 | No trial names, years, or sample sizes appear. |
| 7.6 | It DOES NOT cite effect sizes, relative risks, or statistical results | 🟢 | No numbers of any kind appear in the At-A-Glance text. |
8. Contraindications
| # | Description | Result | Comments |
|---|---|---|---|
| 8.1 | The section is derived from the ER Key Interactions & Contraindications section |
🟢 | All seven items derive from the ER’s two “Populations who should avoid THC” bullets at lines 430 and 432. |
| 8.2 | [stop_items] represent the Contraindications from the ER | 🟢 | Psychiatric history, pregnancy and lactation, hyperemesis history, under-25 regular use, cardiovascular thresholds, Child-Pugh B/C, and tested occupations/athletes — the complete ER set. |
| 8.3 | Individual [stop_items] are formatted as <li></li> | 🟢 | Seven discrete <li> elements inside the stop_items span. |
| 8.4 | Items are as concise as possible. No trailing explanations, no elaborations, no mechanistic rationale, no attributions, no citations, no study details. No content after an em-dash, en-dash, or hyphen-dash (e.g., “— dose reduction required”, “— reduced efficacy”) — these trailing clauses are stripped. Just the key fact. | 🟢 | No trailing dash clauses, rationale, or citations; the ER’s explanatory glosses on the heart-failure class and Child-Pugh score are stripped. |
| 8.5 | Parenthetical qualifiers from the ER bullet — time windows, severity classes, threshold values, clinical staging — ARE preserved as part of the item, kept as concise as possible (shortened or trimmed where needed to fit the one-page budget, but never dropped entirely). | 🟢 | “within 90 days”, “Class III–IV”, “above 160/100 mmHg”, “Class B or C”, “first-degree”, and “approximately 25 years of age” are all retained. |
| 8.6 | When the ER uses ranking notation inside parens (e.g., “>” for severity ordering) that depends on an explanatory phrase to interpret, normalize the items to a plain comma-separated list rather than carrying through the bare symbol. | N/A | The ER contraindication bullets contain no ranking notation inside parentheses. |
| 8.7 | If no [stop_items] are present the section is left empty | N/A | Seven stop_items are present. |
9. Key Interactions
| # | Description | Result | Comments |
|---|---|---|---|
| 9.1 | The section is derived from the ER Key Interactions & Contraindications section |
🟢 | All nine items map one-to-one onto the ER’s nine interaction bullets at lines 412–428. |
| 9.2 | [caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications | 🟢 | No overlap with the Contraindications gate; the two “Populations who should avoid THC” bullets are correctly excluded here. |
| 9.3 | Individual [caution_items] are formatted as <li></li> | 🟢 | Nine discrete <li> elements inside the caution_items span. |
| 9.4 | Items are as concise as possible. No trailing explanations, no elaborations, no mechanistic rationale, no attributions, no citations, no study details. No content after an em-dash, en-dash, or hyphen-dash (e.g., “— dose reduction required”, “— reduced efficacy”) — these trailing clauses are stripped. Just the key fact. | 🟢 | The ER’s “— caution, monitor” qualifiers and all “Mitigation:” clauses are stripped; each item is a class name plus its example list. |
| 9.5 | Parenthetical qualifiers from the ER bullet — example drug lists, time windows, severity classes, threshold values, clinical staging — ARE preserved as part of the item, kept as concise as possible (shortened or trimmed where needed to fit the one-page budget, but never dropped entirely). | 🟢 | Every interaction class retains a representative parenthetical drug list (ketoconazole/clarithromycin/ritonavir/grapefruit juice, rifampicin/carbamazepine/St John’s wort, fluconazole/amiodarone/warfarin, etc.), trimmed but never dropped. |
| 9.6 | When the ER uses ranking notation inside parens (e.g., “>” for severity ordering) that depends on an explanatory phrase to interpret, normalize the items to a plain comma-separated list rather than carrying through the bare symbol. | N/A | The ER interaction bullets contain no ranking notation inside parentheses. |
| 9.7 | If no [caution_items] are present the section is left empty | N/A | Nine caution_items are present. |
10. Protocol
| # | Description | Result | Comments |
|---|---|---|---|
| 10.1 | The section is derived from the ER Protocol section |
🟢 | All three cells derive from ER Therapeutic Protocol lines 462, 468, and 472. |
| 10.2 | The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section |
🟢 | Starting dose and titration, timing of the dose, and single versus split dosing are the three decisions the ER treats as governing. |
| 10.3 | If less that three distinct actionable implementation aspects are mentioned in the ER the unused sets are left empty and made invisible, not filled with placeholder text or empty-state phrasing. | N/A | The ER supplies well more than three actionable aspects; all three sets are used. |
| 10.4 | All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section. |
🟢 | All nine cells carry ER-derived content; the 0.5–2.5 mg start, 2–7 day escalation interval, and 2.5–20 mg target all match ER line 462. |
11. Time to Effect
| # | Description | Result | Comments |
|---|---|---|---|
| 11.1 | The three sets of [time] items cover the three most important time-to-effect aspects from the ER | 🟢 | Oral onset, inhaled onset, and symptomatic onset for pain and spasticity are the only three the ER documents (line 515). |
| 11.2 | The sets are picked and ordered by the magnitude of the related benefit | 🟢 | Oral onset leads because the ER’s high-tier benefits and its standard protocol are oral; inhaled follows; the medium-tier pain and spasticity timeline comes last. |
| 11.3 | If less that three distinct time-to-effect aspects are mentioned in the ER the unused sets are left empty and made invisible, not filled with placeholder text or empty-state phrasing. | N/A | Three distinct time-to-effect aspects are present in the ER; all three sets are used. |
| 11.4 | All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER. | 🟢 | 30 min–3 h with 2–4 h peak, 5–10 min with 15–30 min peak, and 1–2 weeks all match ER line 515 exactly. |
| 11.5 | If the ER does not provide any information on time to effect, the section is removed completely from the Protocol Panel |
N/A | The ER provides time-to-effect information, so the section is correctly retained. |
12. Benefits
| # | Description | Result | Comments |
|---|---|---|---|
| 12.1 | The section is derived from the ER Expected Benefits section |
🟢 | All 13 items correspond to the 13 benefit headings in ER lines 170–248, tier for tier. |
| 12.2 | Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative] | 🟢 | All four spans present and populated. |
| 12.3 | Items are as concise as possible. No explanations, no elaborations, no effect sizes, no qualifiers, no attributions, no citations, no study details, no mechanistic explanations, etc. Just the key fact. | 🟢 | Each tier is a semicolon-separated list of bare benefit names; no NNTs, percentages, or mechanisms are carried over. |
| 12.4 | Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. | 🟢 | No parentheses appear in any benefits item. |
| 12.5 | If no items of a specific sub-section (high, medium, low, speculative) are present the respective is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing. | N/A | All four benefit tiers contain items in the ER. |
13. Risks
| # | Description | Result | Comments |
|---|---|---|---|
| 13.1 | The section is derived from the ER Potential Risks & Side Effects section |
🟢 | All 19 items correspond to the 19 risk headings in ER lines 276–392, tier for tier. |
| 13.2 | Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative] | 🟢 | All four spans present and populated. |
| 13.3 | Items are as concise as possible. No explanations, no elaborations, no effect sizes, no qualifiers, no attributions, no citations, no study details, no mechanistic explanations, etc. Just the key fact. | 🟢 | Each tier is a semicolon-separated list of bare risk names; no odds ratios, prevalences, or mechanisms are carried over. |
| 13.4 | Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. | 🟢 | No parentheses appear in any risks item. |
| 13.5 | If no items of a specific sub-section (high, medium, low, speculative) are present the respective is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing. | N/A | All four risk tiers contain items in the ER. |
14. Monitoring
| # | Description | Result | Comments |
|---|---|---|---|
| 14.1 | The section is derived from the ER Monitoring section |
🟢 | Every row derives from the ER Monitoring Protocol & Defining Success table at lines 541–555. |
| 14.2 | All measurable/quantifiable biomarkers from the Monitoring section are listed |
🟢 | All 13 ER biomarkers are present with matching targets: resting heart rate, seated blood pressure, postural drop, flow-mediated dilation, hs-CRP, fasting insulin, HbA1c, ALT, total testosterone, LH, sperm concentration, bone mineral density, and 12-lead ECG. |
| 14.3 | [monitoring_cadence] is populated with the monitoring cadence/frequency derived from the ER Monitoring section. It is not left with placeholder text or empty. |
🟢 | Baseline within 4 weeks, review at 1 and 4 weeks, vitals at 4 weeks, full panel at 6 months then every 6–12 months, vascular and bone every 12–24 months — matching ER lines 537–539. |
15. Qualitative Assessment
| # | Description | Result | Comments |
|---|---|---|---|
| 15.1 | The section is derived from the ER Monitoring section |
🟢 | All seven items derive from the ER’s qualitative marker list at lines 559–565. |
| 15.2 | All subjective/qualitative biomarkers from the Monitoring section are listed |
🟢 | All seven are present: sleep quality on drug-free nights, morning cognitive clarity, training output, symptom control against baseline, craving and control, mood and anxiety, and appetite pattern. |
Issues 04/08/2026 00:23
Pass rate 100.00%. No issues found.
Issues 04/08/2026 00:17
- 2.5 — Imperative dosing instruction: The [action_1_sub] cell (QRS line 456) reads “escalate by 0.5–2.5 mg every 2–7 days to the lowest effective dose”, a bare imperative that advises rather than presents; the ER (line 462) states it descriptively as “escalation in 0.5–2.5 mg increments no more often than every 2–7 days”.
Fixes 04/08/2026 00:17
- 2.5 — Imperative dosing instruction: Rephrased [action_1_sub] from “Once daily; escalate by 0.5–2.5 mg every 2–7 days to the lowest effective dose” to “Once daily; escalation in 0.5–2.5 mg increments every 2–7 days to the lowest effective dose”, matching the ER’s descriptive phrasing.
Issues 04/08/2026 00:08
- 4.5 — Sheet overflows one A4 page: The rendered sheet runs to roughly 2.3 A4 pages; the Monitoring table (lines 675–876, 13 rows with multi-line “Why” cells and a four-clause cadence) and the Key Interactions gate (lines 599–629, nine items carrying full parenthetical drug lists) are the largest overruns, with the At-A-Glance block, protocol sub-cells, and qualitative descriptions also above their per-section budget.
Fixes 04/08/2026 00:08
- 4.5 — Monitoring “Why” cells condensed: All 13
marker_#_whycells were cut to a single short clause (e.g. “Tachycardia is the most consistent physiological effect; a rising rate signals cumulative sympathetic load” → “Tachycardia is the most consistent physiological effect”), removing roughly 65 pt of table height. - 4.5 — Key Interactions drug lists trimmed: All nine
caution_itemsparenthetical example lists were reduced to their most representative agents (e.g. CYP3A4 inhibitors from seven named drugs to four), taking the CAUTION gate from 23 rendered lines to 17 without dropping any interaction class. - 4.5 — Contraindications tightened: The psychiatric-history, cardiovascular-cluster, and occupational items were reworded more compactly (“Personal or first-degree family history of schizophrenia, schizoaffective or bipolar I disorder”; “Class III–IV heart failure, uncontrolled arrhythmia or hypertension above 160/100 mmHg”), preserving every threshold, time window, and severity class.
- 4.5 — At-A-Glance shortened: Reduced from 57 to 51 words, dropping one rendered line while keeping every Conclusion-derived fact.
- 4.5 — Protocol and Time-to-Effect sub-cells condensed: All six
action_#_sub/time_#_subcells were trimmed to shorter phrasing, cutting one rendered line from each of the two protocol-grid rows. - 4.5 — Monitoring cadence and qualitative items condensed:
monitoring_cadencewas cut from 322 to 228 characters and all sevenqualitative_item_#descriptions were shortened to one rendered line each, with every label kept verbatim.