bruno/MuNa
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Track new Harbor House follow-up issues in beads export

Browse source 
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
Bruno Postle 2026-07-28 08:41:16 +01:00
parent f864004e0a
commit 9b8d2fc1f4
1 changed files with 3 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
.beads/issues.jsonl
View file

@ -13,6 +13,9 @@
{"_type":"issue","id":"ecuador-vay","title":"Generalize a reusable form-language prompt template","description":"The original Postle \u0026 Salingaros paper (buildings-15-02400-v2.txt) only used a\npattern-language fragment as LLM context. This project's key methodological\naddition is pairing that with a form-language grammar (tectonic/spatial/color/\nornament rules) - see ref/Ecuadorian_Form_Language_Grammar.md as the concrete\nexample output for this project.\n\nWe now have the evidence needed to generalize this into a reusable instrument:\n- docs/salingaros-form-language-prompt.md - the actual prompts Salingaros used\n to generate the Ecuadorian form-language grammar (initial + follow-up,\n iterating toward: research vernacular/historical building images across a\n region, synthesize into a generative grammar rather than a style to copy,\n narrow to the specific project's climate/site while drawing vocabulary from\n the wider region, and produce a structured document meant to feed a later\n narrative-generation prompt rather than to generate images directly).\n- ref/Salingaros-Chapter-11-Two-Languages-for-Architecture.md - the theoretical\n basis (pattern language = human/organizational rules, form language =\n geometric/tectonic rules; the two must be linked or the pattern language\n can't connect to built form).\n- ref/Ecuadorian_Form_Language_Grammar.md - the worked example: its structure\n (tectonic sequence, spatial lexicon, composition syntax, color/ornament\n systems with coded references like CR1/OP2/OP4) is the target shape for the\n template's output.\n\nNext step: distill these into a prompt TEMPLATE (with placeholders for region,\nclimate, site, and building-typology specifics) that could be handed to an LLM\nto generate a form-language grammar for any locale/project, in the same\nstructural format as the Ecuadorian example. This is a generalization of the\nmethod, likely relevant to a future paper or revision of the Buildings 2025\nmethodology alongside the existing pattern-language-only approach.","status":"closed","priority":2,"issue_type":"task","assignee":"Bruno Postle","owner":"bruno@postle.net","created_at":"2026-07-24T18:29:07Z","created_by":"Bruno Postle","updated_at":"2026-07-24T18:52:02Z","started_at":"2026-07-24T18:34:49Z","closed_at":"2026-07-24T18:52:02Z","close_reason":"Wrote templates/form-language-prompt-template.md, reviewed for failure modes (hallucination/unverified search claims, region-scale coherence, buildability disclaimer, sacred-motif caution) and applied fixes","dependency_count":0,"dependent_count":0,"comment_count":0}
{"_type":"issue","id":"ecuador-j4n","title":"Write AI image-generation prompts for the counter-proposal's illustrations","description":"Why: docs/counter-proposal.md is the public presentation document and has illustration placeholders throughout (11 markers, several covering more than one distinct scene, ~13 images total) that need to be generated by an AI image tool later, by others (per CLAUDE.md, image generation itself is out of scope for us). For the images to read as one coherent building rather than 13 unrelated renders, the prompts need a shared visual style guide (materials, color palette, massing, ornament placement, mood, rendering medium) repeated/embedded consistently in every individual prompt, plus a scene-specific description grounded in the exact passage of the narrative it illustrates.\n\nWhat: Produce a documented set of detailed image-generation prompts, one per illustration placeholder in docs/counter-proposal.md, each prompt self-contained (includes the full shared style/consistency context, not just a cross-reference) so it can be handed individually to an image generator. Base the visual facts on ref/project-chassis.md (materials strata, CR1 color system executed in plain language, OP2/OP4 ornament) and the relevant narrative passage in docs/counter-proposal.md. Decide file location/format as part of this work.","status":"closed","priority":2,"issue_type":"task","assignee":"Bruno Postle","owner":"bruno@postle.net","created_at":"2026-07-18T20:37:57Z","created_by":"Bruno Postle","updated_at":"2026-07-18T20:47:07Z","started_at":"2026-07-18T20:38:12Z","closed_at":"2026-07-18T20:47:07Z","close_reason":"docs/illustration-prompts.md rewritten: each of the 13 prompts now has the full shared style guide pasted literally inline (no cross-reference placeholder), so any single prompt can be copied straight into an image generator","dependency_count":0,"dependent_count":0,"comment_count":0}
{"_type":"issue","id":"ecuador-cmo","title":"Decide narrative output format/directory layout, update CLAUDE.md Status","description":"Why: CLAUDE.md's Status section explicitly defers this decision: \"Output format,\nfilenames, and directory layout are not yet finalized - decide and record here once the\nnarrative-writing step actually begins.\" That step is about to begin, so this needs\nresolving before narrative-writing tasks are picked up, otherwise each narrative risks\nlanding in an inconsistent location/format.\n\nWhat: Decide (a) directory - likely a new top-level narratives/ - (b) one file per\nstakeholder vs one combined document, (c) filename convention, (d) whether a short\nshared preamble (chassis summary) is prepended/linked in each narrative file for a\nreader encountering only one of them. Update CLAUDE.md's Status section and Deliverable\nsection to record the decision so future sessions don't have to re-derive it.","acceptance_criteria":"CLAUDE.md Status/Deliverable sections state the concrete directory, filenames and per-file structure to use","status":"closed","priority":2,"issue_type":"task","assignee":"Bruno Postle","owner":"bruno@postle.net","created_at":"2026-07-18T19:38:14Z","created_by":"Bruno Postle","updated_at":"2026-07-18T20:03:38Z","started_at":"2026-07-18T20:00:19Z","closed_at":"2026-07-18T20:03:38Z","close_reason":"brief-condensed.md, critique-failures.md, and CLAUDE.md output-format decision all written","dependencies":[{"issue_id":"ecuador-cmo","depends_on_id":"ecuador-7vi","type":"parent-child","created_at":"2026-07-18T20:47:44Z","created_by":"Bruno Postle","metadata":"{}"}],"dependency_count":0,"dependent_count":4,"comment_count":0}
{"_type":"issue","id":"ecuador-0sg","title":"Harbor House: reconcile draft illustration storyboards","description":"projects/harbor-house/docs/images/originals/ has two ChatGPT-generated 9-panel storyboard contact sheets (harbor-house-storyboard-draft.png and harbor-house-storyboard.png) covering the same scenes; unclear which is final or whether to regenerate. Also decide whether to adopt Ecuador's per-scene illustration-prompts.md + one-image-per-placeholder convention instead of a single contact sheet.","status":"open","priority":3,"issue_type":"task","owner":"bruno@postle.net","created_at":"2026-07-28T07:39:18Z","created_by":"Bruno Postle","updated_at":"2026-07-28T07:39:18Z","dependency_count":0,"dependent_count":0,"comment_count":0}
{"_type":"issue","id":"ecuador-sks","title":"Harbor House: decide single vs multi-stakeholder narratives","description":"Ecuador has four stakeholder viewpoints (visitor/staff/school-group/community); Harbor House currently has only one narrative (projects/harbor-house/narratives/sheffield-narrative.md). Decide whether Harbor House needs additional viewpoints (e.g. resident, staff/caseworker, neighbor) for parity, or whether one narrative suffices for its purpose.","status":"open","priority":3,"issue_type":"task","owner":"bruno@postle.net","created_at":"2026-07-28T07:39:10Z","created_by":"Bruno Postle","updated_at":"2026-07-28T07:39:10Z","dependency_count":0,"dependent_count":0,"comment_count":0}
{"_type":"issue","id":"ecuador-gup","title":"Investigate why Salingaros' ChatGPT images read as more compelling than Postle's Midjourney images","description":"Raised while writing the follow-up paper outline (ecuador-lco, paper/outline.md section 4/6/7). Salingaros' ChatGPT-generated images (docs/images-salingaros/) are photo-realistic and, by informal consensus of the authors and July 23 symposium participants, more visually compelling than Postle's Midjourney images (docs/images/), which are looser and watercolour-like. Both tracks used the same pattern subset and form-language grammar as input. Cause is unknown - candidate variables: the generator itself, prompt phrasing differences, how literally each generator resolves the shared form-language vocabulary. Exploratory/optional: a controlled comparison (same narrative text, same style-guide text, run through both generators) would help isolate the variable, if time allows before the paper is finalized.","status":"open","priority":3,"issue_type":"task","owner":"bruno@postle.net","created_at":"2026-07-24T20:45:51Z","created_by":"Bruno Postle","updated_at":"2026-07-24T20:45:51Z","dependency_count":0,"dependent_count":0,"comment_count":0}
{"_type":"issue","id":"ecuador-0u5","title":"Prototype: bubble diagram / plan-layout generation from pattern subset","description":"Exploratory prototype for a possible plan-layout generation stage, raised while planning the follow-up paper (ecuador-lco). Not committed to the paper yet - the paper's 'next steps' section proposes this only as future work in prose. This issue tracks the separate possibility of actually attempting it, which could get folded into the paper if it happens in time.\n\nMotivation (from ref/youtube-transcript-2026-07-23.txt, ~1:02:40-1:03:36): Salingaros' images are individually beautiful but not mutually consistent - 'these are flavors, not solutions' - because there is no shared floor plan behind them. A practicing architect on the call notes 'this Nikos did not create a plan... we need to give a response to the program and ensure that all the spaces work coordinately.'\n\nIdea: the pattern subset (ref/A Pattern Language Ecuador National Museum.md) and project-chassis.md already encode spatial/adjacency relationships (named circulation realms, collection placement, wings) implicitly, via Alexander patterns that are themselves about spatial relationships (e.g. wings of a building, connected buildings, entrance transitions). Investigate whether an LLM can be prompted to derive an explicit bubble diagram / adjacency layout from the pattern subset + brief, that narratives and illustration prompts could then be grounded in consistently, rather than each narrative/image being generated independently.\n\nScope for this issue: research/prototype only - not a commitment to redo the Ecuador narratives or images around it. Output would likely be a new doc (e.g. ref/plan-layout.md or paper/bubble-diagram-experiment.md) showing whether the approach produces something coherent enough to be worth reporting.","status":"open","priority":3,"issue_type":"task","owner":"bruno@postle.net","created_at":"2026-07-24T20:34:59Z","created_by":"Bruno Postle","updated_at":"2026-07-24T20:34:59Z","dependency_count":0,"dependent_count":0,"comment_count":0}
{"_type":"issue","id":"ecuador-e0k","title":"Delete stale ref/ Kimi narrative duplicate","description":"ref/Casa de la Memoria Andina - National Museum Narrative-Kimi.txt is a messier PDF-extraction duplicate of docs/Casa-de-la-Memoria-Andina-National-Museum-Narrative-Kimi.txt (which is the cleaned, canonical copy). Delete the ref/ copy once confirmed nothing else references it.","status":"open","priority":3,"issue_type":"chore","owner":"bruno@postle.net","created_at":"2026-07-24T18:09:17Z","created_by":"Bruno Postle","updated_at":"2026-07-24T18:09:17Z","dependency_count":0,"dependent_count":0,"comment_count":0}
{"_type":"issue","id":"ecuador-0gn","title":"Harbor House: no combined public presentation document yet","description":"Ecuador has docs/counter-proposal.md combining all narratives for publication. Harbor House has only the standalone narrative + docx export, no combined/public-facing document merging narrative and images the way Ecuador's does.","status":"open","priority":4,"issue_type":"task","owner":"bruno@postle.net","created_at":"2026-07-28T07:39:22Z","created_by":"Bruno Postle","updated_at":"2026-07-28T07:39:22Z","dependency_count":0,"dependent_count":0,"comment_count":0}