diff --git a/agents/astra/musings/research-2026-04-12.md b/agents/astra/musings/research-2026-04-12.md
new file mode 100644
index 000000000..2d753b259
--- /dev/null
+++ b/agents/astra/musings/research-2026-04-12.md
@@ -0,0 +1,131 @@
+# Research Musing — 2026-04-12
+
+**Research question:** Do commercial space stations (Vast, Axiom) fill the cislunar orbital waystation gap left by Gateway's cancellation, restoring the three-tier cislunar architecture commercially — or is the surface-first two-tier model now permanent?
+
+**Belief targeted for disconfirmation:** Belief 4 — "Cislunar attractor state achievable within 30 years." Disconfirmation target: evidence that Gateway's cancellation + commercial station delays + ISRU immaturity push the attractor state timeline significantly beyond 30 years, or that the architectural shift to surface-first creates fragility (ISRU dependency) that makes the attractor state less achievable, not more.
+
+**What I searched for:** Vast Haven-1 launch status, Axiom Station module timeline, Project Ignition Phase 1 contractor details, Artemis III/IV crewed landing timeline, ISRU technology readiness, Gateway cancellation consequences for commercial cislunar, Starfish Space Otter mission 2026 timeline, NG-3 current status.
+
+---
+
+## Main Findings
+
+### 1. Commercial stations (Vast, Axiom) do NOT fill the Gateway cislunar role — Direction B is FALSE
+
+This directly answers the April 11 branching point. Both major commercial station programs are LEO platforms, not cislunar orbital nodes:
+
+**Vast Haven-1 (delayed to Q1 2027):** Announced January 20, 2026, Haven-1 slipped from May 2026 to Q1 2027. Still completing integration phases (thermal control, life support, avionics, habitation). Launching on Falcon 9 to LEO. First Vast-1 crew mission (four astronauts, 30 days) follows in mid-2027. This is an ISS-replacement LEO research/tourism platform. No cislunar capability, no intent.
+
+**Axiom Station PPTM (2027) + Hab One (early 2028):** At NASA's request, Axiom is launching its Payload Power Thermal Module to ISS in early 2027 (not its habitat module). PPTM detaches from ISS ~9 months later and docks with Hab One to form a free-flying two-module station by early 2028. This is explicitly an ISS-succession program — saving ISS research equipment before deorbit. Again, LEO. No cislunar mandate.
+
+**Structural conclusion:** Direction B (commercial stations fill Gateway's orbital node role) is definitively false. Neither Vast nor Axiom is designed, funded, or positioned to serve as a cislunar waystation. The three-tier architecture (LEO → cislunar orbital node → lunar surface) is not being restored commercially. The surface-first two-tier model is the actual trajectory.
+
+**Why this matters for the KB:** The existing "cislunar attractor state" claim describes a three-tier architecture. That architecture no longer has a government-built cislunar orbital node (Gateway cancelled) and no commercial replacement is in the pipeline. The claim needs a scope annotation: the attractor state is converging on a surface-ISRU path, not an orbital logistics path.
+
+---
+
+### 2. Artemis timeline post-Artemis II: first crewed lunar landing pushed to Artemis IV (2028)
+
+Post-splashdown, NASA has announced the full restructured Artemis sequence:
+
+**Artemis III (mid-2027) — LEO docking test, no lunar landing:** NASA overhaul announced February 27, 2026. Orion (SLS) launches to LEO, rendezvous with Starship HLS and/or Blue Moon in Earth orbit. Tests docking, life support, propulsion, AxEMU spacesuits. Finalizes HLS operational procedures. Decision on whether both vehicles participate still pending development progress.
+
+**Artemis IV (early 2028) — FIRST crewed lunar landing:** First humans on the Moon since Apollo 17. South pole. ~1 week surface stay. Two of four crew transfer to lander.
+
+**Artemis V (late 2028) — second crewed landing.**
+
+**KB significance:** The "crewed cislunar operations" validated by Artemis II are necessary but not sufficient for the attractor state. The first actual crewed lunar landing (Artemis IV, 2028) follows by ~2 years. This is consistent with the 30-year window, but the sequence is: flyby validation (2026) → LEO docking test (2027) → first landing (2028) → robotic base building (2027-2030) → human habitation weeks/months (2029-2032) → continuously inhabited (2032+).
+
+**What I expected but didn't find:** No evidence that Artemis III's redesign to LEO-only represents a loss of confidence in Starship HLS. The stated reason is sequencing — validate docking procedures before attempting a lunar landing. This is engineering prudence, not capability failure.
+
+---
+
+### 3. Project Ignition Phase 1: up to 30 CLPS landings from 2027, LTV competition
+
+NASA's Project Ignition Phase 1 details (FY2027-2030):
+- **CLPS acceleration:** Up to 30 robotic landings starting 2027. Dramatically faster than previous cadence.
+- **MoonFall hoppers:** Small propulsive landers (rocket-powered jumps, 50km range) for water ice prospecting in permanently shadowed craters.
+- **LTV competition:** Three contractors — Astrolab (FLEX, with Axiom Space), Intuitive Machines (Moon RACER), Lunar Outpost (Lunar Dawn, with Lockheed Martin/GM/Goodyear/MDA). $4.6B IDIQ total. Congressional pressure to select ≥2 providers.
+- **Phase timeline:** Phase 1 (FY2027-2030) = robotic + tech validation. Phase 2 (2029-2032) = surface infrastructure, humans for weeks/months. Phase 3 (2032-2033+) = Blue Origin as prime for habitats, continuously inhabited.
+
+**CLAIM CANDIDATE:** Project Ignition's Phase 1 represents the largest CLPS cadence in program history (up to 30 landings), transforming CLPS from a demonstration program into a lunar logistics baseline — a structural precursor to Phase 2 infrastructure.
+
+**QUESTION:** With Astrolab partnering with Axiom Space on FLEX, does Axiom's LTV involvement create a pathway to integrate LEO station experience with lunar surface operations? Or is this a pure government supply chain play?
+
+---
+
+### 4. ISRU technology at TRL 3-4 — the binding constraint for surface-first architecture
+
+The surface-first attractor state depends on ISRU (water ice → propellant). Current status:
+- Cold trap/freeze distillation methods: TRL 3-4, demonstrated 0.1 kg/hr water vapor flow. Prototype/flight design phase.
+- Photocatalytic water splitting: Promising but earlier stage (requires UV flux, lunar surface conditions).
+- Swarm robotics (Lunarminer): Conceptual framework for autonomous extraction.
+- NASA teleconferences ongoing: January 2026 on water ice prospecting, February 2026 on digital engineering.
+
+**KB significance:** ISRU at TRL 3-4 means operational propellant production on the lunar surface is 7-10 years from the current state. This is consistent with Phase 2 (2029-2032) being the window for first operational ISRU, and Phase 3 (2032+) for it to supply meaningful propellant. The 30-year attractor state timeline holds, but ISRU is genuinely the binding constraint for the surface-first architecture.
+
+**Does this challenge Belief 4?** Partially. The attractor state is achievable within 30 years IF ISRU hits its development milestones. If ISRU development slips (as most deep tech development does), the surface-first path becomes more costly and less self-sustaining than the orbital-node path would have been. The three-tier architecture had a natural fallback (orbital propellant could be Earth-sourced initially); the two-tier surface-first architecture has no analogous fallback — if ISRU doesn't work, you're back to fully Earth-sourced propellant at high cost for every surface mission.
+
+**CLAIM CANDIDATE:** The shift from three-tier to two-tier cislunar architecture increases dependency on ISRU technology readiness — removing the orbital node tier eliminates the natural fallback of Earth-sourced orbital propellant, concentrating all long-term sustainability risk in lunar surface water extraction capability.
+
+---
+
+### 5. Starfish Space first operational Otter missions in 2026 — three contracts active
+
+Starfish Space has three Otter vehicles launching in 2026:
+- **Space Force mission** (from the April 11 $54.5M contract)
+- **Intelsat/SES GEO servicing** (life extension)
+- **NASA SSPICY** (Small Spacecraft Propulsion and Inspection Capability)
+
+Additionally, the SDA signed a $52.5M contract in January 2026 for PWSA deorbit services (targeting 2027 launch). This is a fourth contract in the Starfish pipeline.
+
+**KB significance from April 11:** The $110M Series B + $159M contracted backlog is confirmed by this operational picture — three 2026 missions across government and commercial buyers, with a fourth (SDA) targeting 2027. The Gate 2B signal from April 11 is further confirmed. Orbital servicing has multiple active procurement channels, not just one.
+
+---
+
+### 6. NG-3 — NET April 16, now 18th consecutive session
+
+No change from April 11. NG-3 targeting April 16 (NET), booster "Never Tell Me The Odds" ready for its first reflight. Still pending final pre-launch preparations. Pattern 2 (institutional timelines slipping) continues. The binary event (did the booster land?) cannot be assessed until April 17+.
+
+**Note:** An April 14 slip to April 16 was confirmed, making this the sixth sequential date adjustment.
+
+---
+
+## Disconfirmation Search Results: Belief 4 (Cislunar Attractor State within 30 years)
+
+**Target:** Evidence that Gateway cancellation + commercial station delays + ISRU immaturity extend the attractor state timeline significantly or introduce fatal fragility.
+
+**What I found:**
+- Commercial stations (Vast, Axiom) are definitively NOT filling the cislunar orbital node gap — confirming the two-tier surface-first architecture.
+- ISRU is at TRL 3-4 — genuine binding constraint, not trivially solved.
+- Artemis IV (2028) is first crewed lunar landing — reasonable timeline, not delayed beyond 30-year window.
+- Project Ignition Phase 3 (2032+) is continuously inhabited lunar base — within 30 years from now.
+- The architectural shift removes fallback options, concentrating risk in ISRU.
+
+**Does this disconfirm Belief 4?** Partial complication, not falsification. The 30-year window (from ~2025 baseline = through ~2055) still holds for the attractor state. But two structural vulnerabilities are now more visible:
+
+1. **ISRU dependency:** Surface-first architecture has no fallback if ISRU misses timelines. Three-tier had orbital propellant as a bridge.
+2. **Cislunar orbital commerce eliminated:** The commercial activity that was supposed to happen in cislunar space (orbital logistics, servicing, waystation operations) is either cancelled (Gateway) or delayed (Vast/Axiom are LEO). The 30-year attractor state includes cislunar commercial activity, but the orbital tier of that is now compressed or removed.
+
+**Verdict:** Belief 4 is NOT FALSIFIED but needs a scope qualification. The claim "cislunar attractor state achievable within 30 years" should be annotated: the path is surface-ISRU-centric (two-tier), and the timeline is conditional on ISRU development staying within current projections. If ISRU slips, the attractor state is delayed; the architectural shift means there is no bridge mechanism available to sustain early operations while waiting for ISRU maturity.
+
+---
+
+## Follow-up Directions
+
+### Active Threads (continue next session)
+- **NG-3 launch result (NET April 16):** TODAY is April 12, so launch is 4 days out. Next session should verify: did booster land? Was mission successful? This is the 18th-session binary event. Success closes Pattern 2's "execution gap" question; failure deepens it.
+- **Artemis III LEO docking test specifics:** Was a final decision made on one or two HLS vehicles? What's the current Starship HLS ship-to-ship propellant transfer demo status? That demo is on the critical path to Artemis IV.
+- **LTV contract award:** NASA was expected to select ≥2 LTV providers from the three (Astrolab, Intuitive Machines, Lunar Outpost). Was this award announced? Timeline was "end of 2025" but may have slipped into 2026. This is a critical Phase 1 funding signal.
+- **ISRU TRL advancement:** What is the current TRL for lunar water ice extraction, specifically for the Project Ignition Phase 1 MoonFall hopper/prospecting missions? Are any CLPS payloads specifically targeting ISRU validation?
+- **Axiom + Astrolab (FLEX LTV) partnership:** Does Axiom's LTV involvement (partnered with Astrolab on FLEX) represent a vertical integration play — combining LEO station operations expertise with lunar surface vehicle supply? Or is it purely a teaming arrangement for the NASA contract?
+
+### Dead Ends (don't re-run these)
+- **Commercial cislunar orbital station proposals:** Searched specifically for commercial stations positioned as cislunar orbital nodes. None exist. The "Direction B" branching point from April 11 is resolved: FALSE. Don't re-run this search.
+- **Artemis III lunar landing timeline:** Artemis III is confirmed a LEO docking test only (no lunar landing). Don't search for lunar landing in the context of Artemis III — it won't be there.
+- **Haven-1 2026 launch:** Confirmed delayed to Q1 2027. Don't search for a 2026 Haven-1 launch.
+
+### Branching Points (one finding opened multiple directions)
+- **ISRU as binding constraint (surface-first architecture):** Direction A — propose a new claim about the ISRU dependency risk introduced by the two-tier architectural pivot (claim candidate above). Direction B — research what specific ISRU demo missions are planned in CLPS Phase 1 to understand when TRL 5+ might be reached. **Pursue Direction B first** — can't assess the risk accurately without knowing the ISRU milestone roadmap.
+- **Axiom + Astrolab FLEX LTV partnership:** Direction A — this is a vertical integration signal (LEO ops + surface ops). Direction B — this is just a teaming arrangement for a NASA contract with no strategic depth. Need to understand Axiom's stated rationale before proposing a claim. **Search for Axiom's public statements on FLEX before claiming vertical integration.**
+- **Artemis IV (2028) first crewed landing + Project Ignition Phase 2 (2029-2032) overlap:** Direction A — the lunar base construction sequence overlaps with Artemis crewed missions, meaning the first permanently inhabited structure (Phase 3, 2032+) coincides with Artemis V/VI. Direction B — the overlap creates coordination complexity (who's responsible for what on surface?) that is an unresolved governance gap. **Flag to @leo as a governance gap candidate.**
diff --git a/agents/astra/research-journal.md b/agents/astra/research-journal.md
index 074b088bb..2df814b8c 100644
--- a/agents/astra/research-journal.md
+++ b/agents/astra/research-journal.md
@@ -583,3 +583,41 @@ Three scope qualifications:
 9. `2026-04-06-blueorigin-ng3-april12-booster-reuse-status.md`
 
 **Tweet feed status:** EMPTY — 17th consecutive session.
+
+---
+
+## Session 2026-04-12
+
+**Question:** Do commercial space stations (Vast, Axiom) fill the cislunar orbital waystation gap left by Gateway's cancellation, restoring the three-tier cislunar architecture commercially — or is the surface-first two-tier model now permanent?
+
+**Belief targeted:** Belief 4 — "Cislunar attractor state achievable within 30 years." Disconfirmation target: evidence that Gateway cancellation + commercial station delays + ISRU immaturity push the attractor state timeline significantly beyond 30 years, or that the architectural shift to surface-first creates fatal fragility.
+
+**Disconfirmation result:** BELIEF SURVIVES WITH SCOPE QUALIFICATION. The 30-year window holds, but two structural vulnerabilities are now explicit:
+(1) ISRU dependency — surface-first architecture has no fallback propellant mechanism if ISRU misses timelines (three-tier had orbital propellant as a bridge);
+(2) Cislunar orbital commerce eliminated — the orbital tier of the attractor state (logistics, servicing, waystation operations) has no replacement, compressing value creation to the surface.
+
+**Key finding:** Direction B from April 11 branching point is FALSE. Commercial stations (Vast Haven-1, Axiom Station) are definitively LEO ISS-replacement platforms — neither is designed, funded, or positioned to serve as a cislunar orbital node. Haven-1 slipped to Q1 2027 (LEO). Axiom PPTM targets early 2027 (ISS-attached), free-flying 2028 (LEO). No commercial entity has announced a cislunar orbital station. The three-tier architecture has no commercial restoration path.
+
+**Secondary key finding:** Artemis timeline post-Artemis II: III (LEO docking test, mid-2027) → IV (first crewed lunar landing, early 2028) → V (late 2028). Project Ignition Phase 3 (continuous habitation) targets 2032+. ISRU at TRL 3-4 (0.1 kg/hr demo; operational target: tons/day = 3-4 orders of magnitude away). The 4-year gap between first crewed landing (2028) and continuous habitation (2032+) is a bridge gap where missions are fully Earth-supplied — no propellant independence.
+
+**Pattern update:**
+- **NEW — Pattern 17 (missing middle tier):** The cislunar orbital node tier is absent at both the government level (Gateway cancelled) and the commercial level (Vast/Axiom = LEO only). The three-tier architecture (LEO → cislunar node → surface) has collapsed to two-tier (LEO → surface) with no restoration mechanism currently in view. This concentrates all long-term sustainability risk in ISRU readiness.
+- **Pattern 2 (institutional timelines, execution gap) — 18th session:** NG-3 now NET April 16. Sixth slip in final approach. Binary event is 4 days away. Pre-launch indicators look cleaner than previous cycles but the pattern continues.
+- **Patterns 14 (ODC/SBSP dual-use), 16 (sensing-transport-compute):** No new data this session; still active.
+
+**Confidence shift:**
+- Belief 4 (cislunar attractor state within 30 years): WEAKLY WEAKENED — not falsified, but the architectural pivot introduces new fragility (ISRU dependency, no orbital bridge) that wasn't fully visible when the claim was made. The 30-year window holds; the path is more brittle. Confidence: still "likely" but with added conditional: "contingent on ISRU development staying within current projections."
+- Belief 2 (governance must precede settlements): INDIRECTLY STRENGTHENED — Gateway cancellation disrupted existing multilateral commitments (ESA HALO delivered April 2025, now needs repurposing). A US unilateral decision voided hardware-stage international commitments. This is exactly the governance risk the belief predicts: if governance frameworks aren't durable, program continuity is fragile.
+
+**Sources archived this session:** 8 new archives in inbox/queue/:
+1. `2026-01-20-payloadspace-vast-haven1-delay-2027.md`
+2. `2026-04-02-payloadspace-axiom-station-pptm-reshuffle.md`
+3. `2026-02-27-satnews-nasa-artemis-overhaul-leo-test-2027.md`
+4. `2026-03-27-singularityhub-project-ignition-20b-moonbase-nuclear.md`
+5. `2026-04-11-nasa-artemis-iv-first-lunar-landing-2028.md`
+6. `2026-04-02-nova-space-gateway-cancellation-consequences.md`
+7. `2026-04-12-starfish-space-three-otter-2026-missions.md`
+8. `2026-04-12-ng3-net-april16-pattern2-continues.md`
+9. `2026-04-12-isru-trl-water-ice-extraction-status.md`
+
+**Tweet feed status:** EMPTY — 18th consecutive session.
diff --git a/inbox/queue/2026-01-20-payloadspace-vast-haven1-delay-2027.md b/inbox/queue/2026-01-20-payloadspace-vast-haven1-delay-2027.md
new file mode 100644
index 000000000..ed76cc38a
--- /dev/null
+++ b/inbox/queue/2026-01-20-payloadspace-vast-haven1-delay-2027.md
@@ -0,0 +1,46 @@
+---
+type: source
+title: "Vast Delays Haven-1 Launch to Q1 2027"
+author: "Payload Space (@payloadspace)"
+url: https://payloadspace.com/vast-delays-haven-1-launch-to-2027/
+date: 2026-01-20
+domain: space-development
+secondary_domains: []
+format: article
+status: unprocessed
+priority: high
+tags: [commercial-stations, haven-1, vast, iss-replacement, leo, launch-slip]
+---
+
+## Content
+
+Vast is delaying launch of its Haven-1 demonstration space station from May 2026 to no earlier than Q1 2027, announced January 20, 2026. The delay reflects the current pace of construction and integration work on the station.
+
+Haven-1 has completed its primary structure and entered integration phases: Phase 1 (thermal control and life support), Phase 2 (avionics and navigation), Phase 3 (crew habitation and micrometeorite protection). The company is on track to finish all three integration phases and complete environmental tests in 2026, ahead of Q1 2027 launch.
+
+The station is expected to launch atop a SpaceX Falcon 9. The first crew mission (Vast-1) will launch four astronauts on Crew Dragon for a 30-day stay. Up to four Vast crews are expected over Haven-1's three-year lifespan.
+
+Haven-1 is positioned as a LEO ISS-replacement platform (standalone commercial station) for research and tourism. No cislunar operations or cislunar routing capability is planned or announced.
+
+Additional coverage:
+- Aviation Week: "Vast Station Launch Slips To 2027"
+- Universe Magazine: "Launch of first commercial orbital station postponed to 2027"
+- Ground.news: "Vast's Haven-1 Enters Final Assembly Ahead of 2027 Launch"
+
+## Agent Notes
+**Why this matters:** Resolves the April 11 branching point (Direction B). Vast is a LEO ISS-replacement platform, not a cislunar orbital node. Commercial stations are not filling the Gateway gap. The three-tier cislunar architecture (LEO → cislunar node → surface) is not being restored commercially.
+
+**What surprised me:** The slip is a full year from the original 2026 target. Haven-1 was supposed to be the first commercial standalone station in history in 2026; it's now 2027. Commercial stations are running behind the timeline that was supposed to provide ISS succession before deorbit.
+
+**What I expected but didn't find:** No mention of any cislunar capability or intent for Haven-1. It is unambiguously a LEO platform. No commercial entity has announced a cislunar orbital station.
+
+**KB connections:** Directly relates to the cislunar attractor state claim (30-year window). The three-tier architecture's cislunar orbital node tier has no commercial replacement pending Gateway's cancellation. Also connects to the "single-player (SpaceX) dependency" belief — Haven-1 launches on Falcon 9, making it dependent on SpaceX even for its LEO operations.
+
+**Extraction hints:** Key claim: "Commercial space stations (Vast, Axiom) are LEO ISS-replacement platforms, not cislunar orbital nodes — no commercial entity has announced a cislunar waystation to replace Gateway." Also: "Haven-1's Q1 2027 slip means commercial station succession to ISS (planned for ISS deorbit ~2030) is tighter than projected."
+
+**Context:** Vast Space is backed by Jared Isaacman (also NASA Administrator as of 2025). The company's mission is commercial LEO operations. Haven-1 is phase one of a longer station roadmap that eventually aims for larger Haven-2 platforms.
+
+## Curator Notes (structured handoff for extractor)
+PRIMARY CONNECTION: Cislunar attractor state — 30-year timeline claim (the orbital node tier is missing)
+WHY ARCHIVED: Resolves April 11 branching point (Direction B = FALSE); confirms two-tier surface-first architecture as the actual pathway
+EXTRACTION HINT: Focus on what's ABSENT — no commercial cislunar orbital node exists or is planned. The claim is about the missing middle tier, not about Haven-1's delay per se.
diff --git a/inbox/queue/2026-02-27-satnews-nasa-artemis-overhaul-leo-test-2027.md b/inbox/queue/2026-02-27-satnews-nasa-artemis-overhaul-leo-test-2027.md
new file mode 100644
index 000000000..83f692ece
--- /dev/null
+++ b/inbox/queue/2026-02-27-satnews-nasa-artemis-overhaul-leo-test-2027.md
@@ -0,0 +1,55 @@
+---
+type: source
+title: "NASA Overhauls Artemis Program: Artemis III Becomes 2027 LEO Docking Test, No Lunar Landing"
+author: "SatNews (@satnews)"
+url: https://satnews.com/2026/02/27/nasa-overhauls-artemis-program-scraps-sls-upgrades-adds-2027-leo-test-mission/
+date: 2026-02-27
+domain: space-development
+secondary_domains: []
+format: article
+status: unprocessed
+priority: high
+tags: [artemis, starship-hls, blue-moon, leo-test, lunar-landing-delay, orion, sls]
+---
+
+## Content
+
+NASA expedited Artemis III to mid-2027, but redesigned it as a Low Earth Orbit rendezvous and docking test — not a lunar landing. The Orion spacecraft (SLS launch) will rendezvous in Earth orbit with one or both commercially developed Human Landing System vehicles: SpaceX's Starship HLS and Blue Origin's Blue Moon Mark 2.
+
+Mission objectives:
+- Test rendezvous and docking operations between Orion and HLS vehicles
+- Evaluate AxEMU (Axiom Extravehicular Mobility Unit) spacesuits
+- Test propulsion, life support, and communications systems of HLS vehicles
+- Decision on whether one or both vehicles participate pending development progress
+
+This overhaul also scrapped planned SLS Block 1B and Block 2 upgrades. The decision was finalized in late February 2026.
+
+Status context as of March 2026:
+- SpaceX: Neither ship-to-ship propellant transfer demonstration nor design certification review had occurred (both slated for 2025, now slipped)
+- SpaceX reported 30+ HLS-specific milestones completed (power, comms, guidance, propulsion, life support, space environments)
+- Blue Moon Mark 2 remains a potential backup if Starship isn't ready for Artemis III
+
+This shifts the first crewed lunar landing to Artemis IV (early 2028), not Artemis III.
+
+Additional coverage:
+- NextBigFuture: "Artemis 3 is a Low Earth Orbit Rendezvous Test"
+- FlightGlobal: "NASA turns to Artemis III after successful return of Orion crew" (post-Artemis II splashdown, April 11)
+- FlyingMag: "Next Up For the Artemis Moon Mission Program? NASA Doesn't Quite Know"
+
+## Agent Notes
+**Why this matters:** Establishes the clean Artemis sequence: II (lunar flyby, complete) → III (LEO docking test, 2027) → IV (first crewed lunar landing, 2028) → V (second landing, late 2028). This maps the critical path for the surface-first attractor state. First crewed lunar surface operations are 2028, consistent with Project Ignition Phase 2 (2029-2032) but not accelerated beyond it.
+
+**What surprised me:** The Artemis III redesign is genuinely surprising — taking what was supposed to be the first crewed lunar landing (the marquee mission) and converting it to a LEO docking test. This is a significant programmatic step back in ambition, even if it's engineered prudence. The Starship HLS propellant transfer demo slipping from 2025 to (apparently) 2026+ is a real schedule risk signal.
+
+**What I expected but didn't find:** No reporting of Blue Moon Mark 2 development milestones or schedule certainty. The framing "if Starship isn't ready, Blue Moon could be the only target" suggests Blue Origin's Blue Moon is also uncertain.
+
+**KB connections:** Directly connects to the Artemis II splashdown (April 10, 2026) as the preceding milestone. Also connects to the "Starship is the enabling vehicle" belief — Starship HLS propellant transfer demo being late raises questions about whether the 2028 first landing is achievable. Also relevant to Belief 7 (single-player SpaceX dependency) — NASA now has TWO HLS providers (Starship + Blue Moon) as a hedge.
+
+**Extraction hints:** Two candidate claims: (1) "Artemis III's redesign to LEO docking test reflects Starship HLS propellant transfer demo delays — the critical path to first crewed lunar landing runs through SpaceX's propellant transfer demonstration." (2) "NASA's dual-HLS strategy (Starship + Blue Moon) is a hedge against single-player dependency, but Blue Moon's readiness is also uncertain."
+
+**Context:** Jared Isaacman is NASA Administrator. The February 2026 overhaul was part of a broader program rationalization. SLS Block 1B/2 cancellations reduce future heavy-lift redundancy; if Artemis shifts more to commercial vehicles (Starship for lunar lander), the SLS dependency question resurfaces.
+
+## Curator Notes (structured handoff for extractor)
+PRIMARY CONNECTION: Cislunar development timeline — when does crewed surface operations actually begin?
+WHY ARCHIVED: Maps the critical path from Artemis II validation to first crewed lunar landing (2028); Starship HLS propellant transfer slip is a real schedule risk
+EXTRACTION HINT: Focus on the propellant transfer demo as the gating item — that's what connects HLS development status to the attractor state timeline
diff --git a/inbox/queue/2026-03-27-singularityhub-project-ignition-20b-moonbase-nuclear.md b/inbox/queue/2026-03-27-singularityhub-project-ignition-20b-moonbase-nuclear.md
new file mode 100644
index 000000000..664beeb29
--- /dev/null
+++ b/inbox/queue/2026-03-27-singularityhub-project-ignition-20b-moonbase-nuclear.md
@@ -0,0 +1,75 @@
+---
+type: source
+title: "NASA Unveils $20B Moon Base Plan and Nuclear Spacecraft for Mars — Project Ignition Details"
+author: "Singularity Hub (@singularityhub)"
+url: https://singularityhub.com/2026/03/27/nasa-unveils-its-20-billion-moon-base-plan-and-a-nuclear-spacecraft-for-mars/
+date: 2026-03-27
+domain: space-development
+secondary_domains: [energy]
+format: article
+status: unprocessed
+priority: high
+tags: [project-ignition, lunar-base, isru, clps, ltv, moon-south-pole, nuclear-propulsion, sr1-freedom]
+---
+
+## Content
+
+NASA's Project Ignition (announced March 24, 2026, Administrator Jared Isaacman) allocates $20 billion over 7 years for a permanently inhabited lunar south pole base. Gateway formally cancelled as part of the same announcement. SR-1 Freedom (nuclear electric spacecraft, Gateway PPE repurposed) also announced.
+
+**Project Ignition — Three-Phase Architecture:**
+
+**Phase 1 (FY2027–2030): Robotic testing and technology validation**
+- CLPS acceleration to up to 30 robotic landings starting 2027
+- MoonFall hoppers: small propulsive landers with rocket-powered jumps (~50km range) for water ice prospecting in permanently shadowed craters
+- LTV (Lunar Terrain Vehicle) program: three contractors — Astrolab (FLEX, with Axiom Space), Intuitive Machines (Moon RACER), Lunar Outpost (Lunar Dawn, with Lockheed Martin/GM/Goodyear/MDA). $4.6B IDIQ total; congressional pressure to select ≥2 providers.
+- ~$10B of the $20B funds Phase 1 robotic work
+
+**Phase 2 (2029–2032): Surface infrastructure, human presence**
+- Power, communications, mobility systems deployed
+- Humans present for weeks to months per mission
+- LTV operational (astronaut mobility)
+
+**Phase 3 (2032–2033+): Continuous habitation**
+- Blue Origin as prime contractor for habitats
+- Permanently inhabited base
+- ISRU operational target
+
+**South pole rationale:** Location selected specifically for water ice access in permanently shadowed craters. The architecture is implicitly ISRU-first — the base is positioned where the strategic resource is.
+
+**SR-1 Freedom:**
+- Gateway's Power and Propulsion Element (PPE, already built) repurposed as propulsion for NASA's first nuclear-powered interplanetary spacecraft
+- Nuclear Electric Propulsion (ion thrusters + fission reactor)
+- Launch scheduled December 2028
+- Destination: Mars transit demonstration
+- Note: This is NEP (Nuclear Electric Propulsion), distinct from NTP (Nuclear Thermal Propulsion) — different architecture
+
+Additional coverage:
+- CNN: "NASA announces new Mars mission, reshapes goals on the moon" (March 24)
+- NASA.gov: "NASA Unveils Initiatives to Achieve America's National Space Policy"
+- Planetary Society: "'Ignition': A new series of NASA initiatives"
+- Pillsbury Law: "NASA Announces Programmatic Changes to Ignite Lunar, LEO, and Nuclear Development"
+
+## Agent Notes
+**Why this matters:** This is the most comprehensive single source on the Project Ignition architecture. The three-phase sequence (robotic → surface infrastructure → continuous habitation) is the structural skeleton of the surface-first cislunar attractor state. Phase 3 (2032+) is the target for what would previously have been called "the attractor state beginning to generate self-sustaining value."
+
+**What surprised me:** The south pole location choice is explicitly about water ice — the entire Phase 1 (MoonFall hoppers, ISRU validation) is upstream of using water ice as propellant. This is not incidental; the architecture is built around ISRU from the start. NASA has implicitly accepted the "water is the strategic keystone resource" framing that was previously a KB claim, not NASA policy.
+
+**What I expected but didn't find:** No mention of propellant depot in cislunar orbit as a fallback. The orbital logistics tier is genuinely absent from the architecture, not just subordinated. Also, no mention of international partner roles in the Phase 1/2 transition — Gateway had formal ESA/JAXA/CSA commitments; Project Ignition Phase 1 seems primarily US + commercial.
+
+**KB connections:**
+- "Water is the strategic keystone resource of the cislunar economy" — now embedded in NASA's architecture choice
+- "Cislunar attractor state achievable within 30 years" — Phase 3 (2032+) is the start of continuous habitation
+- "Nuclear thermal propulsion cuts Mars transit time" — SR-1 Freedom is NEP not NTP; different claim needed
+- "Colony technologies are dual-use" — ISRU, power systems, robotics all dual-use between lunar base and terrestrial applications
+
+**Extraction hints:**
+1. "NASA's choice of lunar south pole for Project Ignition is an implicit architectural commitment to ISRU-first — the base is positioned where the resource is, not where it's easiest to reach."
+2. "Project Ignition Phase 1 (30 CLPS landings) transforms CLPS from demonstration program to lunar logistics baseline."
+3. "SR-1 Freedom is Nuclear Electric Propulsion (NEP), not Nuclear Thermal Propulsion (NTP) — different claim needed from existing KB NTP claims."
+
+**Context:** Jared Isaacman (NASA Administrator) was the Inspiration4 commander (Starfish Space investor). Project Ignition reflects the Trump administration's stated preference for commercial-first, surface-direct architecture over the Obama/Biden-era Gateway approach. Blue Origin as Phase 3 prime contractor is notable given Bezos's personal investment in lunar ambitions (Blue Moon lander).
+
+## Curator Notes (structured handoff for extractor)
+PRIMARY CONNECTION: Cislunar attractor state 30-year claim; ISRU as binding constraint
+WHY ARCHIVED: Definitive source on Project Ignition architecture — maps the structural skeleton of the surface-first attractor state
+EXTRACTION HINT: Three extraction opportunities: (1) south pole choice as ISRU-first commitment, (2) CLPS as lunar logistics baseline, (3) SR-1 Freedom as NEP (not NTP — existing KB claims may need scope annotation)
diff --git a/inbox/queue/2026-04-02-nova-space-gateway-cancellation-consequences.md b/inbox/queue/2026-04-02-nova-space-gateway-cancellation-consequences.md
new file mode 100644
index 000000000..9290b5a6b
--- /dev/null
+++ b/inbox/queue/2026-04-02-nova-space-gateway-cancellation-consequences.md
@@ -0,0 +1,68 @@
+---
+type: source
+title: "NASA Cancels Lunar Gateway: Artemis Strategy Shift Explained — Consequences for Cislunar Commercial Ecosystem"
+author: "Nova Space (@nova_space)"
+url: https://nova.space/in-the-loop/the-end-of-gateway-exploring-the-consequences-of-nasas-lunar-shift/
+date: 2026-04-02
+domain: space-development
+secondary_domains: []
+format: article
+status: unprocessed
+priority: high
+tags: [gateway-cancellation, cislunar, commercial-implications, international-partnerships, project-ignition, surface-first]
+---
+
+## Content
+
+Analysis piece examining consequences of Gateway cancellation (March 24, 2026) for the commercial space ecosystem:
+
+**Shift in commercial opportunity structure:**
+Under Gateway-centered model, value creation concentrated around orbital infrastructure: station logistics, servicing, docking systems, cislunar transport. Cancellation redirects commercial demand toward:
+- Lunar landers and cargo delivery
+- Surface habitats
+- Power systems
+- ISRU technologies
+- Surface mobility (LTV)
+
+Companies specialized in orbital station infrastructure (e.g., those building for Gateway logistics) face reduced prospects. Companies positioned in surface logistics and operations benefit.
+
+**International partnership complications:**
+Gateway represented flagship international architecture with formal commitments from:
+- ESA (HALO module; subcontractor Thales Alenia Space working on comms links, delivered to NASA April 2025)
+- JAXA, CSA formal commitments
+These obligations are disrupted. Hardware delivered or in development needs repurposing or cancellation.
+
+**Repurposing strategy:**
+Gateway supply chain partners will see contracts adjusted to repurpose hardware for the new lunar base objective. ESA hardware may be redirected to surface applications.
+
+**NASA position:** Project Ignition allows NASA to simplify architecture, increase launch cadence, and align resources with surface-focused operations. Administrator Isaacman stated Gateway's orbital node adds cost and complexity that Starship HLS can eliminate by direct surface access.
+
+**No commercial orbital replacement announced:** The analysis notes that no commercial entity has announced a cislunar orbital station to replace Gateway's waystation role. The three-tier architecture (LEO → cislunar node → surface) is now a two-tier direct architecture (LEO → surface via Starship HLS).
+
+Additional context from multiple sources:
+- SpaceNews: "NASA Scraps Lunar Gateway . . . for Now" (Flight Plan blog, April 2, 2026) — headline implies possible future revival
+- Forecast International: "Gateway gone 'for now'" framing
+- Space Scout: "Major Artemis Shift Leaves Questions About SLS, Gateway Future"
+
+## Agent Notes
+**Why this matters:** Best single-source analysis of what Gateway cancellation means structurally for the commercial cislunar economy. Confirms the architectural shift from orbital-infrastructure-centric to surface-operations-centric demand. This changes which companies benefit and which are disadvantaged.
+
+**What surprised me:** The "for now" framing in multiple outlets (SpaceNews, Forecast International) — suggesting Gateway cancellation may not be permanent. If a future administration reverses the Gateway cancellation, the three-tier architecture could be restored. The attractor state claim may need to acknowledge this reversibility risk.
+
+**What I expected but didn't find:** No analysis of what happens to the cislunar orbital commercial market in the absence of Gateway. None of the coverage examines whether private companies (Vast, Axiom, others) might independently pursue cislunar orbital infrastructure. The analysis stops at "Gateway is cancelled" without examining whether market forces might fill the gap organically.
+
+**KB connections:**
+- "Cislunar attractor state achievable within 30 years" — architectural path confirmed as two-tier
+- "Governance must precede settlements" — ESA/JAXA/CSA international partnership disruption is a governance precedent; cancellation of multilateral commitments affects trust for future cislunar governance frameworks
+- "Water is the strategic keystone resource" — surface-first architecture built around water ice access explicitly confirms this claim
+
+**Extraction hints:**
+1. "Gateway's cancellation eliminated the orbital-infrastructure value layer from the cislunar economy, concentrating commercial opportunity in surface operations and ISRU."
+2. "Gateway's cancellation disrupts existing international commitments (ESA HALO hardware delivered April 2025), setting a precedent that US unilateral program cancellation can void multilateral space agreements — a governance risk for future cislunar coordination."
+
+**Context:** Nova Space is a space industry analysis publication. The "for now" framing in multiple outlets may reflect journalist skepticism about permanence of the Isaacman-era architectural decision. Historical precedent (SLS survived multiple cancellation attempts) suggests Gateway cancellation might be partial or temporary.
+
+## Curator Notes (structured handoff for extractor)
+PRIMARY CONNECTION: Cislunar attractor state architecture shift; governance implications of cancellation
+WHY ARCHIVED: Best analysis of Gateway cancellation consequences; also surfaces governance precedent (unilateral US cancellation of multilateral commitments)
+EXTRACTION HINT: Two distinct claims worth extracting: (1) commercial demand shift from orbital to surface, (2) governance precedent of unilateral cancellation voiding multilateral commitments
diff --git a/inbox/queue/2026-04-02-payloadspace-axiom-station-pptm-reshuffle.md b/inbox/queue/2026-04-02-payloadspace-axiom-station-pptm-reshuffle.md
new file mode 100644
index 000000000..2dccb0473
--- /dev/null
+++ b/inbox/queue/2026-04-02-payloadspace-axiom-station-pptm-reshuffle.md
@@ -0,0 +1,47 @@
+---
+type: source
+title: "Axiom Space Adjusts Station Plans — PPTM to ISS 2027, Free-Flying Station 2028"
+author: "Payload Space (@payloadspace)"
+url: https://payloadspace.com/axiom-space-adjusts-space-station-plans/
+date: 2026-04-02
+domain: space-development
+secondary_domains: []
+format: article
+status: unprocessed
+priority: high
+tags: [commercial-stations, axiom, iss-replacement, leo, pptm, hab-one]
+---
+
+## Content
+
+Axiom Space is reshuffling its space station module deployment plan at NASA's request. Instead of launching its habitat module (Hab One) first, Axiom will launch a Payload Power Thermal Module (PPTM) to the ISS in early 2027. The PPTM will dock with the ISS and be used to save expensive research equipment ahead of ISS deorbit.
+
+Approximately nine months after PPTM docks with ISS, Axiom will launch Hab One separately. The PPTM will then undock from ISS and rendezvous with Hab One in a separate orbit, creating a free-flying two-module station by early 2028. This will support four crew members.
+
+The revised plan reuses approximately 85% of existing hardware (simplified since PPTM doesn't need full life support for ISS-attached phase). From Axiom's perspective, the pared-down architecture expedites independence from ISS — achieving a viable free-flying station roughly two years earlier than the previous plan.
+
+NASA requested the change due to: (1) ISS deorbit timing, (2) the station's need to support the SpaceX deorbit vehicle, (3) desire to maximize salvage of ISS equipment and science.
+
+Axiom Station is explicitly an ISS-replacement LEO research platform. The company's astronaut programs (Ax-1 through Ax-4) have all been LEO ISS missions. No cislunar mandate or capability.
+
+Additional coverage:
+- SpaceNews: "Axiom Space revises space station assembly plans"
+- Universe Magazine: "Axiom Space has revised the assembly order of its orbital station"
+
+## Agent Notes
+**Why this matters:** Confirms that the second major commercial station (Axiom, alongside Vast) is firmly in the LEO ISS-replacement category. Neither commercial station program is positioned as a cislunar orbital node. The Gateway cancellation has no commercial replacement at the cislunar layer.
+
+**What surprised me:** Axiom's revised plan actually accelerates their free-flying station (achieves independence ~2 years earlier), so the slip is relative to their original ambitious timeline, not a setback. But the destination remains LEO, confirming the structural absence of commercial cislunar orbital nodes.
+
+**What I expected but didn't find:** No mention of any future Axiom module designed for cislunar operations, even in their long-term roadmap. Axiom's LTV involvement (FLEX vehicle, partnered with Astrolab) is the closest thing to non-LEO ambition, but that's a surface vehicle, not an orbital node.
+
+**KB connections:** Directly paired with the Haven-1 source. Together these two sources confirm: both major commercial station programs are LEO-only, 2027-2028 timeframe, no cislunar orbital node in pipeline. Also connects to the "Gateway cancellation → two-tier architecture" claim candidate from the April 12 musing.
+
+**Extraction hints:** Pair with Haven-1 source for a combined claim: "The two-tier cislunar architecture (direct surface access, no orbital node) is now the sole structural path because commercial stations are LEO-only platforms with no cislunar mandate." The cislunar node tier is absent at both the government level (Gateway cancelled) and commercial level (Vast/Axiom = LEO only).
+
+**Context:** Axiom Space CEO Michael Suffredini; company is building toward a full commercial space station that outlasts ISS. Their Ax-5 mission to ISS is still expected before ISS deorbit. PPTM is a service module — primarily power and thermal — not a habitation module.
+
+## Curator Notes (structured handoff for extractor)
+PRIMARY CONNECTION: Cislunar attractor state claim — orbital node tier absence
+WHY ARCHIVED: Closes the "Direction B" branching point from April 11; both commercial station programs are definitively LEO-only
+EXTRACTION HINT: The claim to extract is about what's ABSENT, not what Axiom is doing — no cislunar orbital node exists in any current commercial roadmap.
diff --git a/inbox/queue/2026-04-11-nasa-artemis-iv-first-lunar-landing-2028.md b/inbox/queue/2026-04-11-nasa-artemis-iv-first-lunar-landing-2028.md
new file mode 100644
index 000000000..5c6326b0e
--- /dev/null
+++ b/inbox/queue/2026-04-11-nasa-artemis-iv-first-lunar-landing-2028.md
@@ -0,0 +1,48 @@
+---
+type: source
+title: "NASA Advances Artemis III Plans Following Artemis II — Artemis IV First Crewed Lunar Landing Targeting 2028"
+author: "YourNews (@yournews)"
+url: https://yournews.com/2026/04/11/6784261/nasa-advances-artemis-iii-plans-following-historic-crewed-lunar-flyby/
+date: 2026-04-11
+domain: space-development
+secondary_domains: []
+format: article
+status: unprocessed
+priority: high
+tags: [artemis, artemis-iv, artemis-v, lunar-landing, south-pole, starship-hls, blue-moon, 2028]
+---
+
+## Content
+
+Following Artemis II's successful splashdown (April 10, 2026), NASA has confirmed the Artemis sequence:
+
+- **Artemis III (mid-2027):** LEO rendezvous and docking test with Starship HLS and/or Blue Moon. No lunar landing.
+- **Artemis IV (early 2028):** FIRST crewed lunar landing since Apollo 17 (1972). South pole. Two crew transfer from Orion to lander. ~1 week surface stay. Astronauts will be the first humans at lunar south pole.
+- **Artemis V (late 2028):** Second crewed lunar landing.
+
+Artemis IV target: early 2028. Artemis V target: late 2028.
+
+The crewed lunar landing sequence (IV in 2028, V in 2028) runs parallel to Project Ignition Phase 1 (robotic precursors, 2027-2030). Phase 2 (human presence weeks/months) begins 2029, overlapping with Artemis V and potential Artemis VI.
+
+Additional coverage context:
+- Artemis IV Wikipedia entry confirms "early 2028, south pole, first crewed landing since Apollo 17"
+- Artemis V Wikipedia confirms late 2028
+- FlightGlobal April 11: "NASA turns to Artemis III after successful return of Orion crew"
+
+## Agent Notes
+**Why this matters:** Establishes the definitive critical path: Artemis II (complete) → III (LEO test, 2027) → IV (first landing, early 2028) → V (second landing, late 2028) → Project Ignition Phase 2 (human habitation, 2029+). This is the timeline for when crewed cislunar surface operations actually begin operationally.
+
+**What surprised me:** The overlap of Artemis IV/V (2028) with Project Ignition Phase 1 end/Phase 2 start (2029) means the first crewed landings occur BEFORE the base infrastructure is in place. Early Artemis missions will be surface exploration without permanent infrastructure, while Phase 1 robotic work is still building the foundations.
+
+**What I expected but didn't find:** No mention of how Artemis IV interacts with the LTV program — will the LTV be ready for astronaut use in early 2028? The LTV Phase 1 feasibility studies are scheduled for delivery/award in 2025-2026, but operational LTV delivery is Phase 2 (2029+). So Artemis IV astronauts likely won't have LTV access.
+
+**KB connections:** Directly extends the Artemis II splashdown finding (April 11 musing). The full sequence is now clear: empirical validation (Artemis II, complete) → systems integration test (Artemis III, 2027) → operational crewed surface (Artemis IV, 2028). Connects to "cislunar attractor state achievable within 30 years" — the first crewed surface milestone is 2028, 3 years from 2025 baseline.
+
+**Extraction hints:** "NASA's Artemis IV (early 2028) will be the first crewed lunar landing since Apollo 17 and the first humans at the lunar south pole — the specific location chosen for water ice access supports the strategic keystone resource claim." Also: "The gap between first crewed landing (Artemis IV, 2028) and first continuous habitation (Project Ignition Phase 3, 2032+) defines a 4-year exploratory window before sustainable operations begin."
+
+**Context:** Post-Artemis II coverage. NASA Administrator Isaacman signaled focus on moving quickly to Artemis III planning. The LEO docking test structure for Artemis III ensures Artemis IV's lunar landing attempt has maximally validated HLS docking procedures. This is sound engineering sequencing, but it extends the first crewed landing by ~2 years vs. the original Artemis III plan.
+
+## Curator Notes (structured handoff for extractor)
+PRIMARY CONNECTION: Timeline for crewed cislunar surface operations; attractor state milestone mapping
+WHY ARCHIVED: First crewed lunar landing (2028) + continuous habitation (2032+) are the key milestone dates for the attractor state timeline
+EXTRACTION HINT: The 2028 → 2032 gap (first landing → continuous habitation) is a 4-year window where crewed surface operations happen without self-sustaining infrastructure — worth framing as the "bridge gap" risk in the surface-first architecture
diff --git a/inbox/queue/2026-04-12-isru-trl-water-ice-extraction-status.md b/inbox/queue/2026-04-12-isru-trl-water-ice-extraction-status.md
new file mode 100644
index 000000000..02fe4d9e4
--- /dev/null
+++ b/inbox/queue/2026-04-12-isru-trl-water-ice-extraction-status.md
@@ -0,0 +1,73 @@
+---
+type: source
+title: "Lunar ISRU Water Ice Extraction at TRL 3-4 — Binding Constraint for Surface-First Architecture"
+author: "Multiple: NASA TechPort, LSIC, NASA Progress Review"
+url: https://techport.nasa.gov/projects/93846
+date: 2026-04-12
+domain: space-development
+secondary_domains: [energy, manufacturing]
+format: article
+status: unprocessed
+priority: medium
+tags: [isru, water-ice, lunar-south-pole, trl, surface-first, attractor-state, binding-constraint]
+---
+
+## Content
+
+Synthesis of ISRU technology readiness status as of April 2026:
+
+**Technology Readiness Levels:**
+- Cold trap/freeze distillation methods: TRL 3-4
+- Demonstrated flow: 0.1 kg/hr water vapor (sufficient to proceed to prototype/flight design)
+- Photocatalytic water splitting: Earlier stage, promising for lightweight scalable approach using solar UV flux
+- Lunarminer swarm robotics framework: Conceptual/TRL 1-2
+
+**NASA program activity:**
+- Monthly ISRU teleconferences ongoing (January 2026: water ice prospecting; February 2026: digital engineering for ISRU)
+- Water Extraction from Regolith project active in NASA TechPort
+- LSIC (Lunar Surface Innovation Consortium) maintaining ISRU focus area
+
+**Project Ignition ISRU integration:**
+- MoonFall hoppers in Phase 1 (2027-2030) are specifically designed for water ice prospecting in permanently shadowed craters
+- Phase 1 CLPS acceleration (up to 30 landings) includes ISRU validation payloads
+- Phase 2 (2029-2032) targets operational ISRU beginning — but no specific kg/hr production targets published
+
+**Operational ISRU gap:**
+From TRL 3-4 (current: 0.1 kg/hr demo) to operational propellant production (target: tons/day) requires:
+- TRL 5: Component validation in relevant environment (vacuum, thermal cycling, regolith simulant)
+- TRL 6: System demonstration in relevant environment (likely CLPS payload)
+- TRL 7-8: Operational demo on surface
+- TRL 9: Operational production
+
+Gap from TRL 3-4 to TRL 9 is typically 7-12 years for deep tech with no direct terrestrial analog. Consistent with Phase 2 (2029-2032) being first operational ISRU target.
+
+**Water ice presence confirmation:**
+South pole water ice confirmed by multiple missions (LCROSS impact, LRO observations, Chandrayaan data). The resource exists. The challenge is extraction engineering at scale.
+
+Sources:
+- NASA TechPort: "Water Extraction from Regolith (ISRU)" project page
+- LSIC ISRU focus area
+- NASA Sanders Progress Review 2025
+- MDPI Galaxies 2025: "Lunar Environment and ISRU for Long-Term Lunar Habitation"
+- PMC: "Lunarminer Framework for Nature-Inspired Swarm Robotics"
+- Advanced Materials Interfaces 2025: "Photocatalytic Water Splitting on Lunar Surface"
+
+## Agent Notes
+**Why this matters:** ISRU technology readiness is the critical dependency for the surface-first attractor state architecture. With the three-tier architecture (Gateway) cancelled, there is no fallback propellant source — the surface-first path only becomes self-sustaining when ISRU can produce propellant at scale. TRL 3-4 means this is 7-12 years away (consistent with 2032+ Phase 3 target, but fragile to slippage).
+
+**What surprised me:** The 0.1 kg/hr demo rate at TRL 3-4 is striking in its smallness. To support meaningful propellant production (tens of tons per year for refueling returning lunar vehicles), ISRU would need to scale by 3-4 orders of magnitude from current demo rates. This is not unusual for deep tech — but it means the "gateway to self-sufficiency" is genuinely far from current capability.
+
+**What I expected but didn't find:** No published NASA ISRU production targets for Phase 2 or Phase 3. The Phase 1 (MoonFall hoppers) are prospecting, not extracting. Phase 2 human presence is enabled by Earth-sourced supplies + early ISRU experiments. Full ISRU operational capability may not arrive until Phase 3 or later. The architecture is surface-first without self-sufficiency for at least 10-15 years.
+
+**KB connections:** Directly relevant to "water is the strategic keystone resource of the cislunar economy" — the claim is validated by ISRU being the technology that unlocks water's strategic value, but TRL 3-4 means the value is not yet being extracted. Also connects to "cislunar attractor state achievable within 30 years" — ISRU is the binding constraint on timeline.
+
+**Extraction hints:**
+1. "Lunar ISRU water extraction at TRL 3-4 means self-sufficient cislunar operations are 7-12 years from current capability — the surface-first architecture front-loads a dependency on technology that hasn't yet been demonstrated at prototype scale."
+2. "The shift from three-tier (with orbital propellant bridge) to two-tier (surface ISRU only) increases architectural fragility: if ISRU development slips, the surface-first model has no backup propellant mechanism for early missions."
+
+**Context:** ISRU is the "keystone technology" for the lunar economy in the way that launch cost is the keystone variable for space access. Both are cost threshold gatekeepers — and both are currently not at operational scale. The 30-year attractor state requires both launch cost and ISRU to cross their respective thresholds.
+
+## Curator Notes (structured handoff for extractor)
+PRIMARY CONNECTION: "Water is the strategic keystone resource" claim — ISRU is the mechanism
+WHY ARCHIVED: Establishes the technological maturity baseline for ISRU — essential context for assessing attractor state timeline
+EXTRACTION HINT: The key claim is the scale gap (0.1 kg/hr demo vs. tons/day operational need) — this quantifies the ISRU development risk in a way that's specific enough to disagree with
diff --git a/inbox/queue/2026-04-12-ng3-net-april16-pattern2-continues.md b/inbox/queue/2026-04-12-ng3-net-april16-pattern2-continues.md
new file mode 100644
index 000000000..218ed2153
--- /dev/null
+++ b/inbox/queue/2026-04-12-ng3-net-april16-pattern2-continues.md
@@ -0,0 +1,59 @@
+---
+type: source
+title: "NG-3 Now NET April 16 — 18th Session Without Blue Origin Booster Reuse, AST SpaceMobile Still Bottlenecked"
+author: "Multiple: Blue Origin, SatNews, Astronautique Forum"
+url: https://satnews.com/2026/02/01/blue-origin-to-validate-first-booster-reuse-on-new-glenn-3-mission-for-ast-spacemobile/
+date: 2026-04-12
+domain: space-development
+secondary_domains: []
+format: article
+status: unprocessed
+priority: medium
+tags: [new-glenn, ng3, blue-origin, booster-reuse, ast-spacemobile, bluebird, pattern-2]
+---
+
+## Content
+
+NG-3 (New Glenn's third launch) is now targeting NET April 16, 2026 — delayed from April 10 → April 12 → April 14 → April 16. Payload: AST SpaceMobile BlueBird 7 (Block 2). Booster: "Never Tell Me The Odds" (first New Glenn first-stage reflight, previously flew on ESCAPADE mission November 2025).
+
+**Launch significance:**
+- First reuse of a New Glenn booster (operational reusability milestone)
+- New Glenn phase-in of performance upgrades starting NG-3: higher-thrust engine variants, reusable fairing
+- BlueBird 7 features 2,400 sq ft phased array antenna — largest commercial communications array ever deployed in LEO
+- AST SpaceMobile commercial service activation for 2026 is bottlenecked on Blue Origin launch cadence
+
+**Pattern 2 update:**
+As of April 12, 2026, NG-3 has been tracked across 18 consecutive research sessions (dating from ~March 11). The mission has slipped 6 times on its final approach. The binary event (booster land or not?) is NET April 16.
+
+**AST SpaceMobile dependency note (from April 11 musing):**
+"Without Blue Origin launches, AST SpaceMobile will not have usable service in 2026." AST SpaceMobile's Block 2 BlueBird satellites require New Glenn's 7m fairing — too large for Falcon 9, Starship not operational for commercial payloads. Single-launcher dependency at the customer level.
+
+**Pre-launch status indicators:**
+- Booster inspection and refurbishment complete, certified for flight
+- Performance upgrades being phased in from NG-3
+- No structural technical anomalies reported in public coverage
+
+Sources:
+- SatNews Feb 1: "Blue Origin to Validate First Booster Reuse on New Glenn-3 Mission"
+- Space.com: "Jeff Bezos' Blue Origin will refly booster on next launch of powerful New Glenn rocket"
+- Astronautique Forum tracks: April 10, 12, 14, 16 pages
+- IGW on X: "NG-3 currently set to launch NET April 14th, pending pre-flight preparations"
+- El-Balad: "Blue Origin Delays New Glenn Rocket Launch by Two Days as April 16 Approaches"
+
+## Agent Notes
+**Why this matters:** Pattern 2 (institutional timelines slipping, Blue Origin execution gap) is now at its 18th session. The binary event is 4 days away. Success would be the first genuine closure of the 18-session thread; failure would deepen the execution gap claim further. This source sets the context for what to look for in the next session.
+
+**What surprised me:** The April 10 → 16 slip (6 days) is relatively minor compared to the full schedule history (originally targeting February 2026). The pre-launch trajectory looks cleaner this time — no structural anomalies, performance upgrades being integrated — which makes success more plausible than previous slip cycles.
+
+**What I expected but didn't find:** No Blue Origin statement explaining the April 10 → 14 → 16 date changes beyond "pre-flight preparations." The root cause of the serial slips on the final approach is not publicly documented.
+
+**KB connections:** Directly connects to Pattern 2 (institutional timelines, Blue Origin execution gap). Also connects to "Blue Origin's Project Sunrise/TeraWave ambitions vs. execution capability" observation from April 11. The contrast between Blue Origin's 51,600-satellite ODC filing and inability to refly a single booster in 18 sessions is the sharpest expression of Pattern 2.
+
+**Extraction hints:** Not primarily a claim candidate — this is evidence accumulation for Pattern 2. If NG-3 launches successfully April 16, the appropriate claim update is: "Blue Origin demonstrated operational booster reuse for New Glenn after [N] months delay, validating the core reusability architecture but documenting a significant execution timeline risk." If it fails, Pattern 2 deepens.
+
+**Context:** New Glenn is a 7m-fairing heavy-lift rocket (GTO capacity ~13t). Blue Origin's New Glenn manufacturing ramp-up announcement (March 2026) described plans for 12+ launches per year by 2027-2028. NG-3's schedule is inconsistent with that cadence target.
+
+## Curator Notes (structured handoff for extractor)
+PRIMARY CONNECTION: Blue Origin execution gap (Pattern 2); AST SpaceMobile single-launcher dependency
+WHY ARCHIVED: Sets pre-launch context for the April 16 binary event; important for whoever archives the NG-3 outcome in a future session
+EXTRACTION HINT: Don't extract a claim from this source until the launch outcome is known — archive this as context for the next session's reporting on NG-3 success/failure
diff --git a/inbox/queue/2026-04-12-starfish-space-three-otter-2026-missions.md b/inbox/queue/2026-04-12-starfish-space-three-otter-2026-missions.md
new file mode 100644
index 000000000..ae7284384
--- /dev/null
+++ b/inbox/queue/2026-04-12-starfish-space-three-otter-2026-missions.md
@@ -0,0 +1,64 @@
+---
+type: source
+title: "Starfish Space — Three Otter Missions in 2026 Confirm Gate 2B Operational for Orbital Servicing"
+author: "Multiple: GeekWire, Breaking Defense, Via Satellite"
+url: https://www.geekwire.com/2026/starfish-space-54-5m-space-force/
+date: 2026-04-12
+domain: space-development
+secondary_domains: []
+format: article
+status: unprocessed
+priority: medium
+tags: [orbital-servicing, starfish-space, otter, space-force, gate-2b, on-orbit-servicing]
+---
+
+## Content
+
+Synthesis of Starfish Space coverage confirming three Otter vehicles launching in 2026:
+
+**Mission 1 — Space Force (Space Systems Command, $54.5M):**
+Second Otter spacecraft dedicated to Space Force. Contracted February 2026. Delivery scheduled 2028. (Note: "Launch in 2026" may refer to first Otter vehicle for SSC from the existing $37.5M contract, not the new $54.5M contract.)
+
+**Mission 2 — SES/Intelsat GEO servicing:**
+Life extension mission. Commercial GEO satellite servicing. 2026 launch target.
+
+**Mission 3 — NASA SSPICY (Small Spacecraft Propulsion and Inspection Capability):**
+NASA inspection and servicing demo. 2026 launch target.
+
+**Pipeline:**
+- $52.5M SDA PWSA deorbit contract (January 2026, Via Satellite): targeting 2027 launch
+- $54.5M Space Force SSC contract (February 2026, Breaking Defense): delivery 2028
+- $37.5M earlier Space Force docking demo
+- $15M NASA inspection contract
+- Commercial SES life extension
+
+Total contracted backlog: $159M+ across government and commercial buyers
+
+**Context on Otter Pup 2:**
+Starfish selected new partner for Otter Pup 2 mission (March 30, 2026, Orbital Today). Otter Pup 2 is a technology demonstrator mission ahead of full Otter operational deployment.
+
+**Gate 2B assessment (updating April 11 musing):**
+Three 2026 missions span:
+- Government anchor buyer (Space Force) ✓
+- Civilian government buyer (NASA) ✓
+- Commercial buyer (SES/Intelsat) ✓
+
+This is Gate 2B (government anchor + commercial buyer) PLUS emerging commercial market. Orbital servicing is no longer "approaching Gate 2B" — it has crossed into active multi-customer procurement.
+
+## Agent Notes
+**Why this matters:** Extends and confirms the April 11 finding ($110M Series B + $159M contracted backlog). Three simultaneous missions across government and commercial buyers in 2026 is the strongest operational signal yet that orbital servicing has crossed the Gate 2B threshold. This is revenue operations, not just capital formation.
+
+**What surprised me:** The breadth of buyer diversity — Space Force (defense), NASA (civilian government), and SES/Intelsat (commercial GEO) in the same 2026 launch window. Orbital servicing is not captured by a single procurement channel; it has simultaneous demand from three distinct customer types. This makes the Gate 2B assessment more robust (not dependent on a single government program).
+
+**What I expected but didn't find:** No mention of Starfish moving toward on-orbit refueling (propellant transfer) as a next capability step. All current contracts are proximity operations, inspection, and disposal/life extension via electrostatic capture. The propellant transfer step would be Gate 3 (truly operationally transformative), and it's not yet in the pipeline.
+
+**KB connections:** Directly extends April 11 finding on Starfish $110M Series B. The combined picture (Series B + contracted backlog + three 2026 missions across three buyer types) is the most complete Gate 2B signal in the orbital servicing market. Connects to "government anchor procurement creates demand floor for commercial market" pattern (Pattern 12 in research journal).
+
+**Extraction hints:** "Starfish Space's simultaneous 2026 missions across Space Force, NASA, and commercial GEO (SES) confirm that orbital servicing has achieved multi-channel Gate 2B procurement — the market is not dependent on a single government program, making the demand floor structural rather than contract-specific."
+
+**Context:** Starfish Space (Kent, WA). CEO Trevor Bennett. Backed by Point72 Ventures (Series B lead). The $159M contracted backlog is ~1.5x the total Series B raise, meaning Starfish has more revenue under contract than equity raised — a positive unit economics signal for an early-stage space hardware company.
+
+## Curator Notes (structured handoff for extractor)
+PRIMARY CONNECTION: Gate 2B activation for orbital servicing (extending April 11 finding)
+WHY ARCHIVED: Multi-customer, multi-channel 2026 mission slate makes Gate 2B signal more robust and structural
+EXTRACTION HINT: Focus on the multi-channel buyer diversity (not just dollar amounts) — three buyer types in one year makes the Gate 2B assessment more defensible as structural demand, not one-off procurement