August 20, 2026

Generated lab notebook from daily_summary, plan_journal, plan_delivery_log, and setpoint audit data. It is intentionally chronological and may include in-progress cycles before validation.

Planner Execution Ledger

Planner checkpoints can acknowledge that the active plan is still suitable without writing a new public plan ID. Those no-change decisions are part of the audit trail.

🌅 Morning Cycle (12:20 AM) — iris-20260820-0017

Reflection

Validating previous cycle: iris-20260819-0618

Previous hypothesis: SUNRISE plan for Wednesday 2026-08-19. Tuesday closed at planner score/compliance 64.0, slightly above the 62.4 seven-day average. VPD was the bottleneck at 43.8% versus 51.5% temperature compliance. VPD-high dominated at 10.91 h, narrowly above 9.75 h heat; VPD-low was 0.94 h and cold was 0 h. Dew safety held at an 8.6F minimum margin with 0 risk hours. Reliable cost, electric, gas, and mister-only water fields are unavailable; total water was about 297 gal versus a 201 gal seven-day average, so cooling/misting demand was elevated but utility-cost attribution is not possible. The completed 2026-08-18 SUNRISE plan iris-20260818-0617 was graded 4/10 versus deterministic anchor 2. I gave credit because actual outdoor peak temperature was close to forecast, the predicted heat/VPD-high pattern occurred, VPD-high stayed under the stated 7-hour plan-window bound at 5.35 h, and dew safety held… Result: Revised final evaluation at the SUNRISE replacement boundary. The elapsed MIDNIGHT window scored 43.5 with 46.3% temperature and 41.6% VPD compliance; stress was 0.80 h heat, 0.71 h VPD-high, 0.12 h VPD-low, 0 h cold, and 0 dew-risk hours. Measured VPD recovered to 0.65 kPa inside the active 0.35-0.90 band, the prior moisture-gap alert resolved, and the under-1-hour VPD-low and zero-dew-risk goals succeeded. However, action proof was overwhelmingly guardrail-dependent: 228 of 236 VPD-high guardrail events were held and only 8 dispatched, so the plan decisively failed its below-25% held-event experiment and cannot claim clean causal execution. The later hot/dry fallback was unobserved before SUNRISE replacement. Revised grade 3/10 versus deterministic anchor 1: limited credit for physiological recovery and safety, with the two-point gap reflecting those measured outcomes; weak corridor compliance and 96.6% held delivery dominate the score. Score: 3/10

Hypothesis

Testing: Use a short live-edge recovery bridge before the humid trough, then restage moisture and thermal authority ahead of the rapid hot-dry ramp; test whether guardrail-aligned intent cuts the prior plan’s 90.6% held-event fraction while preserving dew safety. Expected outcome: By 02:00 MDT, house VPD is inside or within 0.10 kPa of the active high edge and the vent-vpd moisture-gap condition clears. From 02:00-08:15, dew-risk remains 0 h and VPD-low stress stays below 1.0 h. If SUNRISE replacement is delayed, band-coupled moisture and precooling are available by 09:30 before corrected VPD exceeds about 1.5 kPa; residual midday heat is treated as physics-limited. Fewer than 25% of this plan’s VPD-high guardrail events should be held.

Setpoints

Thursday August 20

Primary crop-band changes:

Tactical tunable changes:

Changed secondary parameters:

🌅 Morning Cycle (6:24 AM) — iris-20260820-0619

Reflection

Validating previous cycle: iris-20260820-0017

Previous hypothesis: MIDNIGHT review and new-day posture for Thursday 2026-08-20. Prior local day: legacy planner score/compliance closed at 59.2, below the 61.4 seven-day average. Temperature and VPD legacy axes were both weak at 48.2% and 49.2%; stress was dominated by 10.77 h heat and 7.72 h VPD-high, with 2.48 h VPD-low, 0 h cold, and no reported dew-risk. Reliable cost and mister-only resource terms are unavailable, so no efficiency claim is made. Previous-plan validation: iris-20260819-0618 is finalized at 5/10 versus deterministic anchor 3. Its high-heat window matched at 5.23 h and its explicit VPD-high-under-6-hour goal was met at 3.75 h despite solar reaching 1224 W/m2 versus 782 predicted. However scoped compliance was only 55.6, VPD-low reached 1.20 h, and 5 of 9 VPD-high guardrail events were held… Result: The completed 06:24-19:51 MDT SUNRISE window scored 54.0, with temperature compliance 45.0% and VPD compliance 37.2%. Stress was 3.68 h heat, 3.80 h VPD-high, 0.78 h VPD-low, 0 h cold, and 0 dew-risk hours. The predicted high heat and VPD-high kinds were correct, but actual heat was below the expected 5-8 h structural range while VPD-high stayed well below the stated 8 h ceiling. The dawn VPD-low window was directionally right, but the under-0.5 h low-side goal failed at 0.78 h. Band-coupled moisture and 0.15 fog escalation preserved dew safety and VENT_COOL_FOG_ASSIST improved both temperature and VPD error in recent response priors. However, VPD remained the compliance bottleneck, 5.02 h of fog and the roughly 20-22 s pulse-gap posture coincided with bidirectional VPD stress, and total water was 356 gal versus the 183 gal seven-day average; mister-only water and reliable cost terms were unavailable, so resource efficiency cannot be graded. Delivery was not clean: 34 plan expectations were missed, including repeated cool-stage-2 expectations and direct_wet_stress_latest_hour remaining 21 instead of 24. The held-event experiment therefore lacks clean success evidence even though the physiological VPD-high bound succeeded. Final self-grade 5/10: credit stress bounds, zero dew risk, and useful wet-assist response, but penalize weak 54.0 corridor compliance, VPD-low overshoot, high total water, and substantial delivery misses. Score: 5/10

Hypothesis

Testing: Hold one stable, guardrail-aligned +0.05/+0.20-0.25 kPa hot/dry moisture posture from the confirmed ramp through measured evening recovery, rather than clock-tapering it, and test whether held VPD-high guardrail events fall below 50% while dew-risk remains zero. Expected outcome: Through 00:30 MDT, dew-risk remains 0 h; VPD-low stress stays under 0.5 h; plan-window VPD-high stress stays under 8 h despite corrected outdoor VPD above 4 kPa; heat stress is expected to remain structurally limited to roughly 5-8 h. During live hot/dry VENTILATE, wet-assist authority remains band-coupled and fewer than 50% of VPD-high guardrail events are held, improving materially on the prior plan’s 228/236 held events.

Conditions

Clear extreme hot/dry ramp through 17:00, then variable to overcast evening. Raw VPD peaks at 4.96 kPa; bounded calibrated planning prior remains above 4 kPa.

Expected stress windows

Parameter rationale

Setpoints

Thursday August 20

Primary crop-band changes:

Tactical tunable changes:

Changed secondary parameters:

🌆 Evening Cycle (7:56 PM) — iris-20260820-1951

Reflection

Validating previous cycle: iris-20260820-0619

Previous hypothesis: SUNRISE plan for Thursday 2026-08-20. Yesterday closed at legacy planner score/compliance 59.2, below the 61.3 seven-day average. Temperature was the slightly weaker legacy axis at 48.2% versus 49.2% VPD, while heat dominated at 10.77 h, followed by 7.72 h VPD-high, 2.48 h VPD-low, and 0 h cold. Dew safety held at a 7.8F minimum with 0 risk hours. Reliable cost, electricity, gas, and mister-only water fields are unavailable, so cost attribution is not claimed; assembled total water was 210 gal versus a 181 gal seven-day average, and runtime was cooling/fog dominated. The completed 2026-08-19 SUNRISE plan iris-20260819-0618 is graded 5/10 versus deterministic anchor 3. It correctly predicted high heat and VPD-high pressure, kept its scoped VPD-high burden to 3.75 h, and preserved dew safety despite actual solar reaching 1224 W/m2 versus 782 predicted. It still delivered only 55… Result: Final evaluation at the 2026-08-21 MIDNIGHT replacement boundary for the elapsed 19:51-00:17 MDT SUNSET window. Scoped planner score/compliance was 31.2, temperature compliance 40.0%, and VPD compliance 24.8%. Scoped stress was only 0.02 h heat, 0.02 h VPD-high, 0 h VPD-low, 0 h cold, and 0 dew-risk hours, so the numeric under-2.0 h VPD-high, under-0.5 h VPD-low, zero-cold, and zero-dew-risk bounds were met. However the primary physiological hypothesis failed: current VPD is 1.22 kPa versus the active 0.94 kPa high edge and temperature is 72.9F in VENTILATE; alert 10374 reports VPD-high with no moisture assist, and east is 1.32 kPa. The intended recovery bridge did not clear the high edge by midnight. Delivery was not clean: 4 expectations were guardrailed, 2 held, and 3 missed; repeated vpd-high moisture guardrails held the requested wider gap/fog-off taper, while direct_wet_stress_latest_hour and dew-margin requests did not materialize. The pre-dawn and 07:30 fallback goals were unobserved before replacement. Grade 3/10: limited credit for dew/cold safety and low scoped stress totals, but weak corridor compliance, a failed recovery endpoint, an open moisture-gap alert, and poor causal delivery dominate. Score: 3/10

Hypothesis

Testing: Use a short band-coupled evening recovery bridge followed by staged, wider overnight moisture spacing; test whether VPD clears the live high edge by midnight while VPD-low and dew-risk remain bounded and relay churn falls. Expected outcome: By 00:30 MDT, measured VPD should clear the active high edge without dew-risk, then remain within the overnight corridor through pre-dawn. Plan-window VPD-high stress should stay under 2.0 h, VPD-low under 0.5 h, cold stress at 0 h, and dew-risk at 0 h. Mister/fog authority should taper after recovery, reducing overnight relay churn and avoiding a repeat of today’s bidirectional VPD stress. If SUNRISE replacement is delayed, the 07:30 fallback should open demand-coupled moisture and thermal lead before the forecast 100-101F/10% RH ramp without pre-wetting the cool dawn air.

Conditions

Clear dry evening easing to a mild 63F pre-dawn, followed by an abrupt extreme hot-dry ramp. Overnight raw VPD falls from 2.89 to 0.95 kPa; Friday peaks near 101F, 10% RH, and 840 W/m2 raw solar.

Expected stress windows

Parameter rationale

Setpoints

Thursday August 20

Primary crop-band changes:

Tactical tunable changes:

Friday August 21

Primary crop-band changes:

Tactical tunable changes:

Changed secondary parameters:

End-of-Day Summary

Climate

Interior Light Evidence

• Crop DLI: unavailable
• Reason: source_reading_missing
• Provenance: legacy_invalid_exterior_proxy_plus_fixture_estimate
• Validity: dli-validity-v1; 2024-01-01T00:00:00+00:00 → open
• Qualified-light minutes and photoperiod remain independent of unavailable DLI.

Stress Hours

• Heat stress (>85°F): 7.2h
• VPD stress (>2.0 kPa): 14.9h
• Cold stress (<55°F): 7.4h

Economics

Equipment Runtimes

Water

• Total: 370 gal
• Mister: 122 gal

Crop Health (Gemini Vision)

Hourly Pattern

7-Day Stress Context