May 18, 2026
Generated lab notebook from daily_summary, plan_journal, and setpoint audit data. It is intentionally chronological and may include in-progress cycles before validation.
🌅 Morning Cycle (5:46 AM) — iris-20260518-0543
validated
7/10
bias_cool, bias_heat, d_cool_stage_2, d_heat_stage_2, dwell_gate_ms, enthalpy_close, enthalpy_open, fog_escalation_kpa ...
Result: Plan-window scorecard for the 2026-05-18 SUNRISE cold/wet suppression plan: score 73.7 with 75.0% both-axis compliance, temp compliance 75.3%, VPD compliance 84.3%, heat stress 0.22h, cold stress 0.90h, VPD-high 0.00h, VPD-low 0.05h, cost about USD 0.60 in the plan window. Full-day partial score by sunset improved to 87.0 with 88.6% both-axis compliance, temp 88.9%, VPD 99.5%, 0 dp-risk hours, and only 8 gal water. Hypothesis was mostly validated: conservative moisture posture kept VPD-low and condensation essentially at zero, while bias_cool +4 and gas staging bounded cold stress. Remaining score loss was mostly temp/cold-band alignment and gas cost from a cold saturated day, not VPD control failure.
Reflection
Validating previous cycle: iris-20260517-2014
Previous hypothesis: SUNSET overnight plan for Sunday 2026-05-17. Today’s score improved sharply versus the 7-day trend (80.1 vs 50.4) with both-axis compliance 76.6%, low cost USD 0.85 vs USD 4.79, and no dew-point risk. VPD-high was still the largest stress (3.23h), but the current and forecast risk has shifted: house VPD is now 0.50 kPa with RH 78% and a safe 7.1F dew margin, while the next 12h are cold, saturated, cloudy/rainy, and fall to 41-45F with outdoor VPD near 0.05-0.10 kPa. I evaluated the governing SUNRISE plan at 6/10 versus anchor 3; my grade is higher because the operator-level VPD-low, dew-risk, water, and VPD-high targets mostly succeeded, while the anchor penalized 171 guardrail events and the plan missed heat/compliance targets after actual solar exceeded forecast. Tonight I am suppressing mist/fog, shortening any sealed-mist residence, using wide VPD hysteresis, restoring safe nonzero timing/readback values where manual rows drifted, and using bias_cool +4 with modest heat/gas staging to prevent heater-to-vent chatter without raising crop bands.
{"conditions":{"outdoor_temp_peak_f":54.0,"outdoor_rh_min_pct":76.0,"solar_peak_w_m2":0,"cloud_cover_avg_pct":100,"notes":"Cold wet overnight: 54F at 21:00 falling to 41-42F by dawn, RH 76-95%, raw outdoor VPD 0.34 falling to 0.05 kPa, 100% cloud/rain. Current house is 66.9F, VPD 0.50 kPa, RH 78%, dew point 59.8F, dew margin 7.1F, IDLE. Main risks are VPD-low/condensation pressure and heater-to-vent oscillation, not dry-air VPD-high."},"stress_windows":[{"kind":"vpd_low","start":"2026-05-17T20:20:00-06:00","end":"2026-05-18T08:00:00-06:00","severity":"medium","mitigation":"Suppress mist/fog with engage 2.2-2.4, all 2.5, 60s gaps, 900s mist delays, fog_escalation 0.95-1.0, vpd_hysteresis 0.50, and short 120s sealed cap."},{"kind":"cold","start":"2026-05-18T01:00:00-06:00","end":"2026-05-18T08:00:00-06:00","severity":"medium","mitigation":"Use bias_heat 1.5-1.75, bias_cool 4.0, d_heat_stage_2 3.0, heat_hysteresis 1.5, and dwell gate on to use gas staging for sustained cold without heater-to-vent chatter."}],"rationale":[{"parameter":"bias_cool","old_value":3.5,"new_value":4.0,"forecast_anchor":"Forecast falls below 45F after 03:00 with heating likely; high-confidence lessons use +3 to +4 to prevent heater-to-vent oscillation.","expected_effect":"Keep cold stress under 1h overnight and avoid vent dumps after heater overshoot."},{"parameter":"bias_heat","old_value":0.75,"new_value":1.5,"forecast_anchor":"Cold wet night reaches 41-42F with rain/high RH; use modest warmth rather than raising crop bands.","expected_effect":"Hold stable 63-66F greenhouse and keep dew margin above 5F with gas/slab support."},{"parameter":"d_heat_stage_2","old_value":5.0,"new_value":3.0,"forecast_anchor":"Sustained <45F period from about 03:00-08:00 validates the heating lesson favoring gas for real cold.","expected_effect":"Shift sustained cold support to gas staging and avoid excessive electric-only runtime."},{"parameter":"mister_engage_kpa","old_value":1.3,"new_value":2.2,"forecast_anchor":"Current VPD is 0.50 and forecast outdoor VPD collapses to 0.05-0.10; retrieved lessons say avoid mist until live VPD actually rises.","expected_effect":"Prevent new VPD-low and keep mist water near zero overnight."},{"parameter":"mister_all_kpa","old_value":1.5,"new_value":2.5,"forecast_anchor":"No dry-air window overnight; all-zone mist should be effectively unavailable unless an unexpected VPD-high event occurs.","expected_effect":"Avoid over-humidifying the cool house."},{"parameter":"fog_escalation_kpa","old_value":1.0,"new_value":1.0,"forecast_anchor":"Fog is blocked overnight and conditions are saturated; conservative fog posture should persist until a live daytime dry ramp is observed.","expected_effect":"No unnecessary fog/condensation pressure overnight."},{"parameter":"mist_max_closed_vent_s","old_value":120.0,"new_value":120.0,"forecast_anchor":"Dew margin is safe but forecast RH is 90-95%; keep sealed-mist residence short if it is ever entered.","expected_effect":"Keep dp_risk_hours at 0."},{"parameter":"vpd_hysteresis","old_value":0.5,"new_value":0.5,"forecast_anchor":"Cool wet night with localized VPD spread and likely low-band edge behavior; preserve wide deadband.","expected_effect":"Reduce humidity/dehum oscillation and false mist starts."},{"parameter":"heat_hysteresis","old_value":0.0,"new_value":1.5,"forecast_anchor":"Current readback showed a manual zero row; safety lesson forbids zero timers/rails and prior plan used nonzero heat hysteresis.","expected_effect":"Restore stable heater clearing behavior and prevent rapid heat cycling."}]}Result: Plan-window scorecard for the 2026-05-18 SUNRISE cold/wet suppression plan: score 73.7 with 75.0% both-axis compliance, temp compliance 75.3%, VPD compliance 84.3%, heat stress 0.22h, cold stress 0.90h, VPD-high 0.00h, VPD-low 0.05h, cost about USD 0.60 in the plan window. Full-day partial score by sunset improved to 87.0 with 88.6% both-axis compliance, temp 88.9%, VPD 99.5%, 0 dp-risk hours, and only 8 gal water. Hypothesis was mostly validated: conservative moisture posture kept VPD-low and condensation essentially at zero, while bias_cool +4 and gas staging bounded cold stress. Remaining score loss was mostly temp/cold-band alignment and gas cost from a cold saturated day, not VPD control failure. Score: 7/10
New finding: Cold wet overcast days with outdoor VPD near 0.1-0.3 kPa validate high moisture thresholds, conservative fog escalation, wide VPD hysteresis, short sealed-mist residence, and bias_cool +4 with gas staging; success should be judged by VPD-low and dp-risk avoidance plus bounded cold stress rather than water use alone. → Added to Lessons Learned
Hypothesis
Conditions: Cold wet overcast day: outdoor 38-44F, RH 85-100%, raw outdoor VPD 0.00-0.13 kPa, rain probability high through afternoon, and current house is 64.5F, VPD 0.48 kPa, RH 77%, dew margin 7.4F, IDLE with heat1 on. Primary risks are VPD-low/condensation pressure and heater-to-vent/heat overshoot, not dry-air VPD-high. | outdoor peak: 44.0, RH min: 85.0, solar peak: 294.0, cloud cover: 96.0 | stress windows: vpd_low 2026-05-18T05:45:00-06:00-2026-05-18T23:00:00-06:00 medium; cold 2026-05-18T05:45:00-06:00-2026-05-18T23:00:00-06:00 medium; heat 2026-05-18T10:30:00-06:00-2026-05-18T15:30:00-06:00 low Testing: All-day cold/wet suppression with daytime bias_heat trim: test whether high moisture thresholds plus bias_cool +4 and gas staging keep VPD-low/dp-risk at zero while reducing heat overshoot versus the overnight posture. Expected outcome: By tonight: planner score >80, both-axis compliance >80%, VPD compliance >95%, VPD-low 0h, dp-risk 0h, cold stress <1.5h, heat stress <1.0h, mister/fog water near zero, and total daily cost below the 7-day average.
Conditions (structured)
44.0°F
85.0%
294.0 W/m²
96.0%
Cold wet overcast day: outdoor 38-44F, RH 85-100%, raw outdoor VPD 0.00-0.13 kPa, rain probability high through afternoon, and current house is 64.5F, VPD 0.48 kPa, RH 77%, dew margin 7.4F, IDLE with heat1 on. Primary risks are VPD-low/condensation pressure and heater-to-vent/heat overshoot, not dry-air VPD-high.
Expected stress windows
Keep mister_engage_kpa 2.35-2.45, mister_all_kpa 2.5, 60s gaps, 900s mist delays, fog_escalation 1.0, vpd_hysteresis 0.50, and mist_max_closed_vent_s 120s.
Use d_heat_stage_2 3.0, heat_hysteresis 1.5, dwell gate ON, and bias_cool +4.0; keep bias_heat modest during day and restore 1.75 in the evening as outdoor falls toward the high 30s.
Avoid over-driving heaters through the small solar/rainy midday window by trimming bias_heat to 1.25 while keeping wide cooling bias to prevent vent dumps.
Parameter rationale
Reduce heater overshoot/heat stress while keeping cold stress under about 1.5h using gas staging and slab retention.
Prevent vent dumps after heater overshoot and keep cold stress bounded.
Keep VPD-low near 0h and misting water near zero unless an unexpected live VPD rise occurs.
Avoid fog-driven condensation and keep dp_risk_hours at 0.
Maintain minimum dew margin above 5F.
Reduce ordinary mode churn without blocking safety or thermal-relief exits.
Setpoints
Monday May 18
Primary crop-band changes:
Immediate sunrise cold/wet posture: suppress mist/fog, keep
Morning rain block: outdoor VPD stays near zero; keep moistu
Wet midday with possible small solar pulse: trim heat bias t
Peak rain/cold period and forecast solar blip: remain humidi
Evening cold returns with little solar: restore stronger hea
Cold saturated overnight handoff: continue gas-friendly heat
Tactical tunable changes:
Immediate sunrise cold/wet posture: suppress mist/fog, keep
Morning rain block: outdoor VPD stays near zero; keep moistu
Wet midday with possible small solar pulse: trim heat bias t
Peak rain/cold period and forecast solar blip: remain humidi
Evening cold returns with little solar: restore stronger hea
Cold saturated overnight handoff: continue gas-friendly heat
Changed secondary parameters:
initial 4
initial 1.5
initial 3
initial 300000
initial 1
initial -2
initial 1
initial 1.5
initial 180
initial 45
initial 180
initial 120
initial 60
initial 60
initial 2400
initial 120
initial 90
initial 900
initial 900
initial 600
initial 600
initial 1
initial 1
initial 1
initial 1
initial 1
initial 2
initial 5
initial 5
initial 120
1.5 → 1.25
1.25 → 1.75
Full secondary parameter dump
Value 4.
Value 1.5.
Value 3.
Value 300000.
Value 1.
Value -2.
Value 1.
Value 1.5.
Value 180.
Value 45.
Value 180.
Value 120.
Value 60.
Value 60.
Value 2400.
Value 120.
Value 90.
Value 900.
Value 900.
Value 600.
Value 600.
Value 1.
Value 1.
Value 1.
Value 1.
Value 1.
Value 2.
Value 5.
Value 5.
Value 120.
Value 4.
Value 1.5.
Value 3.
Value 300000.
Value 1.
Value -2.
Value 1.
Value 1.5.
Value 180.
Value 45.
Value 180.
Value 120.
Value 60.
Value 60.
Value 2400.
Value 120.
Value 90.
Value 900.
Value 900.
Value 600.
Value 600.
Value 1.
Value 1.
Value 1.
Value 1.
Value 1.
Value 2.
Value 5.
Value 5.
Value 120.
Value 4.
Value 1.25.
Value 3.
Value 300000.
Value 1.
Value -2.
Value 1.
Value 1.5.
Value 180.
Value 45.
Value 180.
Value 120.
Value 60.
Value 60.
Value 2400.
Value 120.
Value 90.
Value 900.
Value 900.
Value 600.
Value 600.
Value 1.
Value 1.
Value 1.
Value 1.
Value 1.
Value 2.
Value 5.
Value 5.
Value 120.
Value 4.
Value 1.25.
Value 3.
Value 300000.
Value 1.
Value -2.
Value 1.
Value 1.5.
Value 180.
Value 45.
Value 180.
Value 120.
Value 60.
Value 60.
Value 2400.
Value 120.
Value 90.
Value 900.
Value 900.
Value 600.
Value 600.
Value 1.
Value 1.
Value 1.
Value 1.
Value 1.
Value 2.
Value 5.
Value 5.
Value 120.
Value 4.
Value 1.75.
Value 3.
Value 300000.
Value 1.
Value -2.
Value 1.
Value 1.5.
Value 180.
Value 45.
Value 180.
Value 120.
Value 60.
Value 60.
Value 2400.
Value 120.
Value 90.
Value 900.
Value 900.
Value 600.
Value 600.
Value 1.
Value 1.
Value 1.
Value 1.
Value 1.
Value 2.
Value 5.
Value 5.
Value 120.
Value 4.
Value 1.75.
Value 3.
Value 300000.
Value 1.
Value -2.
Value 1.
Value 1.5.
Value 180.
Value 45.
Value 180.
Value 120.
Value 60.
Value 60.
Value 2400.
Value 120.
Value 90.
Value 900.
Value 900.
Value 600.
Value 600.
Value 1.
Value 1.
Value 1.
Value 1.
Value 1.
Value 2.
Value 5.
Value 5.
Value 120.
🌆 Evening Cycle (8:15 PM) — iris-20260518-2012
Daily Summary So Far
not validated yet
bias_cool, bias_heat, d_cool_stage_2, d_heat_stage_2, dwell_gate_ms, enthalpy_close, enthalpy_open, fog_escalation_kpa ...
Reflection
Daily Summary So Far — this cycle will be validated at the next planning cycle.
Hypothesis
Conditions: Cold saturated overnight: outdoor 40F at sunset falling to 37-38F pre-dawn, RH 84-89%, raw outdoor VPD 0.09-0.12 kPa, 100% cloud, no meaningful solar. Current house is 63.3F, VPD 0.46 kPa, RH 78%, dew margin 7.2F, IDLE with heat1 on. Main challenge is stable gas/electric heating and avoiding VPD-low/condensation, not VPD-high. | outdoor peak: 40.0, RH min: 84.0, solar peak: 24.0, cloud cover: 100.0 | stress windows: cold 2026-05-18T22:00:00-06:00-2026-05-19T07:30:00-06:00 medium; vpd_low 2026-05-18T20:20:00-06:00-2026-05-19T08:30:00-06:00 low Testing: Cold saturated overnight restoration: test whether high mist thresholds plus bias_cool +4 and modest bias_heat +2 at the coldest hours keep VPD-low and dp-risk near zero while reducing cold stress versus today. Expected outcome: By Tuesday sunrise: VPD-high 0h, VPD-low under 0.25h, dp-risk 0h, cold stress near or below 1h, paired compliance above 80% for the overnight window, and cost dominated by gas but remaining proportional to sub-40F weather.
Conditions (structured)
40.0°F
84.0%
24.0 W/m²
100.0%
Cold saturated overnight: outdoor 40F at sunset falling to 37-38F pre-dawn, RH 84-89%, raw outdoor VPD 0.09-0.12 kPa, 100% cloud, no meaningful solar. Current house is 63.3F, VPD 0.46 kPa, RH 78%, dew margin 7.2F, IDLE with heat1 on. Main challenge is stable gas/electric heating and avoiding VPD-low/condensation, not VPD-high.
Expected stress windows
bias_cool 4.0, bias_heat 1.75 rising to 2.0 at coldest hours, d_heat_stage_2 3.0, heat_hysteresis 1.5, dwell gate ON, and normal nonzero heat timers to prevent heater-to-vent oscillation while allowing sustained gas support.
mister_engage_kpa 2.35-2.45, mister_all_kpa 2.5, 60s pulse gaps, 300/600s mist delays, fog_escalation 1.0, vpd_hysteresis 0.50, and 120s sealed-mist cap. This also protects dew-point margin because structured hypothesis only allows heat/cold/vpd_high/vpd_low stress kinds.
Parameter rationale
Prevent physical misting overnight and keep VPD-low under 0.25h with dp-risk at 0h.
Keep all-zone mist unavailable unless an unexpected severe VPD spike occurs.
Avoid short humidity pulses during transient VPD noise.
Avoid all-zone mist rotation overnight.
Reduce VPD-low and water use without increasing VPD-high stress.
Keep cold stress near or below 1h overnight while maintaining dew margin above 5F.
Avoid vent dumps after heater overshoot and keep heat/cold whipsaw low.
Maintain dp_risk_hours at 0.
Reduce dehum/mist chatter while preserving safety.
Setpoints
Monday May 18
Primary crop-band changes:
evening_settle: restore conservative saturated-night moistur
mid_evening_cold_deepening: outdoor near 39F, saturated and
Tactical tunable changes:
evening_settle: restore conservative saturated-night moistur
mid_evening_cold_deepening: outdoor near 39F, saturated and
Tuesday May 19
Primary crop-band changes:
coldest_saturated_block: forecast 38F, RH near 89%, outdoor
pre_dawn_hold: outdoor still 38F with no solar; hold heating
morning_handoff_fallback: if the sunrise cycle is delayed, r
Tactical tunable changes:
coldest_saturated_block: forecast 38F, RH near 89%, outdoor
pre_dawn_hold: outdoor still 38F with no solar; hold heating
morning_handoff_fallback: if the sunrise cycle is delayed, r
Changed secondary parameters:
initial 4
initial 1.75
initial 3
initial 300000
initial 1
initial -2
initial 1
initial 1.5
initial 180
initial 45
initial 180
initial 120
initial 60
initial 60
initial 2400
initial 120
initial 90
initial 600
initial 300
initial 600
initial 600
initial 1
initial 1
initial 1
initial 1
initial 1
initial 2
initial 5
initial 5
initial 120
1.75 → 1.85
1.85 → 2
4 → 3.5
2 → 1.5
Full secondary parameter dump
Value 4.
Value 1.75.
Value 3.
Value 300000.
Value 1.
Value -2.
Value 1.
Value 1.5.
Value 180.
Value 45.
Value 180.
Value 120.
Value 60.
Value 60.
Value 2400.
Value 120.
Value 90.
Value 600.
Value 300.
Value 600.
Value 600.
Value 1.
Value 1.
Value 1.
Value 1.
Value 1.
Value 2.
Value 5.
Value 5.
Value 120.
Value 4.
Value 1.85.
Value 3.
Value 300000.
Value 1.
Value -2.
Value 1.
Value 1.5.
Value 180.
Value 45.
Value 180.
Value 120.
Value 60.
Value 60.
Value 2400.
Value 120.
Value 90.
Value 600.
Value 300.
Value 600.
Value 600.
Value 1.
Value 1.
Value 1.
Value 1.
Value 1.
Value 2.
Value 5.
Value 5.
Value 120.
Value 4.
Value 2.
Value 3.
Value 300000.
Value 1.
Value -2.
Value 1.
Value 1.5.
Value 180.
Value 45.
Value 180.
Value 120.
Value 60.
Value 60.
Value 2400.
Value 120.
Value 90.
Value 600.
Value 300.
Value 600.
Value 600.
Value 1.
Value 1.
Value 1.
Value 1.
Value 1.
Value 2.
Value 5.
Value 5.
Value 120.
Value 4.
Value 2.
Value 3.
Value 300000.
Value 1.
Value -2.
Value 1.
Value 1.5.
Value 180.
Value 45.
Value 180.
Value 120.
Value 60.
Value 60.
Value 2400.
Value 120.
Value 90.
Value 600.
Value 300.
Value 600.
Value 600.
Value 1.
Value 1.
Value 1.
Value 1.
Value 1.
Value 2.
Value 5.
Value 5.
Value 120.
Value 3.5.
Value 1.5.
Value 3.
Value 300000.
Value 1.
Value -2.
Value 1.
Value 1.5.
Value 180.
Value 45.
Value 180.
Value 120.
Value 60.
Value 60.
Value 2400.
Value 120.
Value 90.
Value 600.
Value 300.
Value 600.
Value 600.
Value 1.
Value 1.
Value 1.
Value 1.
Value 1.
Value 2.
Value 5.
Value 5.
Value 120.
Daily Summary So Far
Climate
61.7–76.5°F; avg 67.8°F
0.33–1.23 kPa; avg 0.67 kPa
60.9–83.4%
Stress Hours
- Heat stress (>85°F): 0.5h
- VPD stress (>2.0 kPa): 0.0h
- Cold stress (<55°F): 2.1h
Economics
USD 0.05
USD 3.27
USD 0.040
USD 3.36
Equipment Runtimes
Primary exhaust runtime.
Secondary exhaust runtime.
Intake vent runtime.
Fogger runtime.
Electric heater runtime.
Gas heater runtime.
Supplemental lighting runtime.
South mister runtime.
West mister runtime.
Center mister runtime.
Water
- Total: 8 gal
- Mister: 0 gal
Crop Health (Gemini Vision)
Observation notes are collapsed below to avoid publishing partial vision snippets.
Observation notes are collapsed below to avoid publishing partial vision snippets.
Observation notes are collapsed below to avoid publishing partial vision snippets.
Observation notes are collapsed below to avoid publishing partial vision snippets.
Observation notes are collapsed below to avoid publishing partial vision snippets.
Vision observation notes
Canna Lilies appear healthy with robust foliage visible in the IR image.
Hanging orchids appear healthy with green foliage.
Seedlings appear healthy and are establishing well.
Seedlings are growing, but some variation in size is visible.
Seedlings are growing steadily.
Hourly Pattern
RH 66.1%.
RH 70.0%.
RH 62.3%.
RH 57.7%.
RH 67.3%.
RH 70.1%.
RH 66.3%.
RH 62.1%.
RH 76.4%.
RH 75.6%.
RH 78.6%.
RH 80.5%.
RH 81.1%.
RH 81.0%.
RH 80.0%.
RH 79.4%.
RH 79.3%.
RH 78.5%.
RH 75.8%.
RH 73.5%.
RH 69.9%.
RH 66.4%.
RH 64.3%.
RH 64.0%.
7-Day Stress Context
Cold stress 0.7h.
Cold stress 0.6h.
Cold stress 0.0h.
Cold stress 0.2h.
Cold stress 0.1h.
Cold stress 0.4h.
Cold stress 2.1h.