Design Memory Platform

Technical diary

6 records · 2 decisions · 2 moments · 1 features · 1 tickets
D144 rebirthadoptedDesign LanguageDecision09 Jul 2026

MHAL Blender prototype is a ringfenced, Claude-owned standalone - GALF-conformant, GAAD untouched

The MHAL Blender explorer (MHAL_Prototype_0_008.py, evolved from an uploaded 0_005c) is a standalone prototype that Claude (Specification Owner) owns and iterates. It is ringfenced from the GAAD platform 'for now': it lives outside the bundle, adds no GAAD records or pipeline dependencies, and no MHAL work modifies GAAD scripts. The fence only comes down on Miles's explicit instruction. Even while ringfenced, the prototype is built to STRICTLY ALIGN with MHAL v0.003 and HONOUR GALF v0.005 - it emits the platform contact-point stamp (language/language_version/galf_version), the MHAL type-level and per-instance relationship triples, the honest City>District>Block hierarchy, the Scale Resolution Axis, and per-concept status - so its JSON can port into GAAD later without rework.

D145 newacceptedNamingDecision09 Jul 2026

Two senses of 'architecture' kept apart; GALF retained over ALF

The word 'architecture' carries two unrelated senses in GAAD and they are kept distinct. (1) The design-school sense - 'architectural language' as the grammar of a building (the architectural language of Fallingwater) - stays lowercase in prose and is formalised as the platform term 'Architectural Language' (a GALF-conforming language: PRAL/GRAL/MHAL/FWAL/TWAL). (2) The system-structure sense - how the framework, languages, connector and engine connect - is named 'The Architecture' (capitalised) only as a website page/section title, never as a bare noun in prose. The framework keeps its agreed name GALF (GAAD Architectural Language Framework); the proposed rename to 'ALF' is rejected.

P053 Design LanguageMoment09 Jul 2026

First coloured MHAL block with legend renders - GALF proven portable to a ringfenced standalone

The MHAL standalone (0_008) rendered its Manhattan block coloured by MHAL term - blue Building parcels rising off the charcoal Block, the gold Plot grid showing through, greens between the towers, street trees ringing the edge - with a standing 'MHAL objects' legend of coloured swatches beside it. Miles: 'This is looking great and I am pleased you have ownership of this now with a ringfence to GAAD (for now).'

P054 VisionMoment09 Jul 2026

The browser dream - GAAD beyond Blender, renderer as a swappable adapter

Miles named a possible endpoint: 'Perhaps at some point we can ditch Blender and have GAAD in a browser with web access to ALs - this might be a dream. We only use say 5% of Blender, so perhaps a home-grown solution / desktop app could be the way to go in the future.' Raised while the neutrality of GALF (engine-free by s10) and the genome->phenotype connector design were fresh.

F031 parkedPlatformFeature09 Jul 2026

Website + AI as the primary read interfaces (with searchable, live records)

INSIGHT (Miles, 09 Jul 2026): 'if i am looking for a record, I ask you or go to the website as it is easy to use.' In practice the two interfaces GAAD is actually read through are (a) the website and (b) asking an AI seat. The JSON source of truth, generators and bundle structure are PLUMBING that Miles does not touch by hand. This reframes priorities: the website is not a side publish artefact, it is the primary reading room, and the AI seat is the primary retrieval method - so both must be first-class and trustworthy. FEATURE CONSEQUENCES to build: 1. Website live data - records on the site should reflect live record data, not a snapshot frozen at publish time. If the website is the primary reader, a stale website is stale memory. (Supersedes the earlier 'live data on hold' note - this raises its priority.) 2. Website record search/filter - a search or filter box so 'find me the NASA thing' works ON THE SITE the way it works when asking the AI. The flat-table-with-category-filter pattern (audit/Records Hub) is the starting point; extend to free-text search across records. 3. Website always in the bundle - the reading room must travel with the project, never be orphaned as a separate zip (see the standing website-in-bundle rule). 4. AI retrieval must be disciplined - the primary 'ask Claude' path depends on the handover rules: search-first, do-not-parrot, verify-then-state (HANDOVER READ FIRST section). An AI that guesses instead of reading the records breaks the interface Miles relies on daily. Also captured this session and related: the daily audit log as a shareable blog post (one HTML page per day, native 4bim theme, deep-links into record HTMLs, opens with a records scoreboard). A website 'Daily' index page (daily.html) and publishing the daily series are the immediate follow-ons. PARKED: not started. Recorded so the strategic steer is not lost. Priority raised from 'on hold' to a recognised primary-interface concern.

T021 mediumopenGeneratorTicket09 Jul 2026

GAAD has no ??AL connector contract - languages can be defined but not run through world/stages/lineage

Proposed (spec on hold per Miles, 09 Jul 2026 - ticket raised to record the gap, spec deferred): a NEW platform-side spec, working name 'GAAD Language Connector', referencing GALF but living in Spec/ not inside GALF (honours s10). It would define the runtime verbs every runnable ??AL implements - describe / random_genome(world) / build(genome, world, ctx) / mutate / breed / serialize / deserialize - plus the build context GAAD passes (origin, stage collection, generation, stage_id, parent_stage_id). Core shift for each language: seed -> explicit gene array so mutation has locality and breeding can recombine; build() must be pure (RNG only in random_genome) so replay is bit-exact (replay-never-mutation). Minimal MHAL delta when the fence comes down: split plan_block(seed) into random_genome + pure plan_from_genome; add mutate/breed/serialize(.CEL)/deserialize; add build_into(ctx); wrap as MHALConnector with the standalone panel as a thin caller so it still runs alone. Two three-seat decisions to settle first: (a) confirm the connector is a separate spec referencing GALF, not part of GALF; (b) whether GALF should REQUIRE any language with platform_status=active to ship a conforming connector (contractual vs convention).