Eve library

Oshun presentation center

Guide

Revision 2

On this page

Eve two-track edition, 9 September 2026: after the user's review of the Eve section, its 25 guides are merged into twelve chapters on two tracks, Use Eve and How Eve works, with every existing slide retained and a teal second accent for Eve-owned surfaces. Chapter 1, Meet Eve, is the delivered specimen of the new Eve edition: a chapter cover with listening time, an actor map that fixes the four canonical actors and their colours, glyph cards in place of tables, the real Explorer capture with numbered callouts, and a close that bridges to the next chapter. The four-planes diagram now matches its own narration. Nine tracks were rendered; all twelve chapter PDFs were re-exported and checked. The library has 75 guides, 1,359 unique slides and complete narration. The brief records the diagnosis and decisions; the receipt records the evidence. Chapters 2 to 12 carry their inherited slides until each is rewritten in the same system. Counts below are historical checkpoints.

Living Scenes integrated delivery, 2026-09-09: the Creation sequence now moves from runtime into composition, the complete technique catalog, compatibility and admission, Compose Assist, governance, and finally the actual consumer surfaces. The combined library has 84 guides, 1,150 unique slides, 1,173 guide-slide instances and 537 cited source paths. The 44-slide technique package and 47-slide consumer package retain their independent source, browser, PDF and narration evidence. Their shared 1,059-slide baseline and narration entries are unchanged; the two addition sets are disjoint. Integration restored the omitted living-consumer-secrets recording and tightened the customer-card headline so its product view fits the compact desktop reader. The integration receipt binds the combined route, preservation and final checks. Full V1, native-device and human acceptance remain open. Counts in the delivery checkpoints below are historical.

Living Scenes consumer delivery checkpoint, 2026-09-09: the 47-slide guide follows the actual customer card and fixture compose workspace into keep, sharing, tenant policy, rendering, durable media, public playback, accessibility and distribution. Five real UI captures accompany source-shaped relationships, gates and disposition matrices. The PDF and 45.6 minutes of new narration are delivered; all 1,059 recordings and all 81 guide HTML files from the integrated remote revision remain exact. At this standalone checkpoint the library had 82 guides, 1,106 unique slides, 1,129 guide-slide instances and 534 cited source entries. Forty complete source units are newly bound through 61 teaching records, bringing global coverage to 150 reviewed, 10,018 structural and 103,176 unassigned units. The guide credits the server-owned policy, render-admission, durable-media and APNG-download repairs while retaining explicit score, privacy, accessibility, caller and release gaps. Its receipt is complete for this increment. The full V1 audit, remaining creation systems, native-device and human acceptance remain open. Counts below describe historical checkpoints.

Technique delivery checkpoint · 9 September 2026: what reached the slides separates the delivered Eve fixes from the unfinished whole-library design work. Eve retains 25 guides and 217 slides. Living Scenes now adds a 25-slide technique catalog and a 19-slide compatibility guide between the composition workflow and Compose Assist. They teach all twelve technique records, all nine primitive contracts, continuity scorecards, four policy stops, seven scoring dimensions, the complete template matrix and the limits of the current callers. At this standalone checkpoint the library contained 83 guides, 1,103 unique slides, 1,126 guide-slide instances and 507 cited source paths. See the technique delivery evidence. Full V1, whole-library design and human acceptance remain open. Counts below are historical checkpoints.

Living Scenes correction delivery · 9 September 2026: the 16-slide runtime guide now includes five corrected explanations and three adjacent detail slides, with updated PDF and eight regenerated recordings. It shows validator differences, cue priority, actual scheduling states and reconnect limits. The verification receipt records the scoped source, visual, browser and narration evidence. The library has 79 guides and 1,028 unique slides; no complete handbook unit is newly assigned. Full V1, broader Living Scenes and human acceptance remain open. Earlier counts below are historical checkpoints.

Tara Mentor Presence delivery, 2026-09-09: the 43-slide guide explains the synthetic cast, score, settings, arrivals, posture, choreography, cadence, release dossiers, rendered media, private storage, preferences, fallback, disclosure and analytics. Three real component crops accompany relationships, records, decision diagrams and timelines. The PDF and 62.8 minutes of new narration are delivered; all 982 prior slides and recordings remain intact. The library now has 79 guides, 1,025 unique slides and 1,048 guide-slide instances. Twelve complete source sections are newly bound to teaching evidence; Tara has 18 reviewed, 2 structural and 10 unassigned units. The guide distinguishes the implemented tonal render from the intended embodied experience and records observed product gaps. Its receipt is complete for this increment. The full V1 audit, Living Scenes consumer audit, native-device and human acceptance remain open. Counts below describe historical checkpoints.

Teacher and ritual integration, 2026-09-09: the teacher guide — since merged into chapter five of the Tara track — and incoming ritual assembly/tone guide are now combined: 52 slides and 53.9 minutes of narration beyond the shared 930-slide baseline. The library has 78 guides, 982 unique slides, 1,005 guide-slide instances and 466 cited paths, all with complete narration. The integration receipt preserves both deliveries and records the one corrected ritual-table overflow. Tara has 17 reviewed, 2 structural and 11 unassigned handbook units. Mentor Presence, Living Scenes, the remaining V1 audits and human/native acceptance remain open in the full V1 workstream. Counts below describe historical checkpoints.

Tara teacher delivery, 2026-09-09: the new twenty-two-slide guide — since merged into chapter five of the Tara track — explains the canonical teacher record and the actual directory: identity, lineage, roles, locales, rights, voice, search, generated reviews, availability, content links and recovery. Two real component crops accompany relationships, records and decision diagrams. It includes a PDF and 27.7 minutes of narration. The receipt preserves all 930 earlier slides and recordings. The library now has 77 guides, 952 unique slides, 975 guide-slide instances and 457 cited paths. The complete Teachers handbook unit is newly reviewed; Tara has 15 reviewed, 2 structural and 13 unassigned units. Seeded profiles, generated reviews and weekday displays are explicitly qualified. Mentor Presence, Living Scenes, connected service evidence and human acceptance remain open within the full V1 audit. Counts below describe historical checkpoints.

Tara ritual, reflection and companion integration, 2026-09-09: the ritual assembly and tone guide joins the incoming reflection and companion guides on current main. The library has 77 guides, 960 unique slides, 983 guide-slide instances and 460 cited paths, all with complete narration. The integrated Tara handbook has sixteen reviewed, two structural and twelve unassigned units; global reviewed coverage is 94. The integration receipt binds all three histories, current generated artifacts, narration preservation and focused browser/center/PDF evidence. Full V1 work remains active; delivery counts below are historical checkpoints.

Tara companion delivery, 2026-09-09: the new twenty-eight-slide guide explains all six offers, their selection and attribution, Metis reflection-topic analysis, Veritas/Sophia evidence labels and Assistant context transfer. It includes a complete PDF and 34.5 minutes of narration. The receipt preserves all 902 earlier slides and recordings. The library now has 76 guides, 930 unique slides, 953 guide-slide instances and 451 cited paths. One complete handbook unit is newly reviewed; Tara is at 14 reviewed, 2 structural and 14 unassigned units. Native Metis note wiring, destination verification, Iris persistence and human acceptance retain explicit qualifications. The full V1 audit remains active. Counts below are historical.

Combined Tara delivery, 2026-09-09: reflection and continuation and the incoming duration, context and lineage guide are integrated. Together they add 48 slides and 55.1 minutes of narration to the 854-slide baseline. The current library has 75 guides, 902 unique slides, 925 guide-slide instances and 429 cited paths. The integration receipt binds both authored deliveries, their unchanged recordings and all 48 reviewed PDF pages. The full V1 audit remains active; subsequent counts below describe historical checkpoints.

Tara reflection delivery, 2026-09-09: the new twenty-four-slide guide explains the native route, all five prompt families and fifteen starters, Save/Skip/Edit/Done, completion projection and the next Continue action. Relationship, transition and gate diagrams make identity and state changes explicit. It includes a complete PDF and 30.3 minutes of narration. The receipt binds source cases, rendered review and exact preservation of all 854 earlier slides and recordings. The library now has 74 guides, 878 unique slides, 901 guide-slide instances and 426 cited paths. The guide characterizes pinned behavior; native lifecycle, durable note recovery, human acceptance and the remaining full V1 work stay open. Counts below are historical.

Tara context and offline-audio integration, 2026-09-09: the new duration, context and lineage guide joins the three audio guides and five selection-taxonomy assignments on current main. The library has 74 guides, 878 unique slides, 901 guide-slide instances and 427 cited paths, all with complete narration. All 854 baseline scripts, manifest entries and MP3 bytes remain exact. Three new source-unit assignments advance the Tara handbook to thirteen reviewed, two structural and fifteen unassigned units; global reviewed coverage is 91. The delivery receipt retains 14 source cases, 172 browser checks, focused center/PDF evidence and the unresolved application-consumer boundary. Full V1 work remains active.

Tara offline audio delivery, 2026-09-09: the new twenty-slide guide follows enrollment, checksums, quality and media fallback, recent retention, budgets and clearing. It has a complete PDF and 25.2 minutes of narration. The receipt records exact source cases, rendered-page review and preservation of all 834 earlier slides and recordings. The library now contains 73 guides, 854 unique slides, 877 guide-slide instances and 424 cited paths. This teaches the pinned implementation and its limits; native-device, reflection and other full V1 work remain open. Counts below are historical.

Tara audio and selection integration, 2026-09-09: the library now combines 72 guides, 834 unique slides, 857 guide-slide instances and 420 cited paths, all with complete narration. The 42 audio pages and the five incoming Tara taxonomy assignments are retained together. The integration receipt records the current center review, exact export-pixel comparisons and unchanged recordings. Delivery counts below are historical checkpoints. The full V1 program remains active.

Tara audio delivery, 2026-09-08: shared audio state and native playback add 42 slides, complete PDFs and 48.5 minutes of narration. The pair explains legal phase transitions, interruption, listening time, markers, native launch ordering, controls and recovery. All 792 prior slides/scripts/recordings and 70 prior guide HTML files remain exact. The library now has 72 guides, 834 unique slides, 857 guide-slide instances and 420 cited paths. The receipt retains scoped source, visual, accessibility, PDF and audio evidence. Earlier counts below are historical. The full V1 program and native-device, storage, reflection and companion acceptance remain open.

Tara selection source-unit assignment, 2026-09-08: five complete taxonomy units now bind to seventeen exact pages in the existing Tara selection guide: the canonical catalog boundary, mood, theme, modality and cadence sections. The source-scoped inventory advances to ten reviewed, two structural and eighteen unassigned units; global reviewed coverage advances from 83 to 88. The library remains at 70 guides, 792 unique slides, 815 guide-slide instances, 416 cited paths and 792 unchanged recordings. The assignment receipt records the exact unit/heading/fingerprint regression, 316 browser checks, focused center/PDF verification and current limits. Full V1 work remains active.

Tara selection and complete Eve operations integration, 2026-09-08: the current library has 70 guides, 792 unique slides, 815 guide-slide instances and 416 cited paths, all with complete narration. The two Tara guides remain unchanged and Eve operations now ends with its five-document reading map. The final integration receipt records current review and exact reuse. Counts below are historical checkpoints; full V1 work remains active.

Tara selection and Eve release integration, 2026-09-08: the current library has 70 guides, 791 unique slides, 814 guide-slide instances and 416 cited paths. Both new Tara guides and the incoming Eve release-evidence page are complete. Every guide HTML file and all 791 recordings retain their owning bytes. The integration receipt records current center/PDF checks and exact reuse. Earlier counts below are historical checkpoints. Full V1 work remains active.

Tara selection and handoff delivery, 2026-09-08: two linked guides add 44 slides: moods, themes and modalities and Tara–Lilith practice handoff. The complete feature catalogs, constraint cases, type priority and thirteen rule summaries now have readable references, record specimens, relationships and branches. New narration totals 58.5 minutes, with complete PDFs. All 746 earlier slides and recordings and 68 earlier guide HTML files remain exact. The library now has 70 guides, 790 unique slides, 813 guide-slide instances and 415 cited paths. The receipt retains source, visual, accessibility, PDF and audio evidence. Earlier counts below are historical; full V1 work remains active.

Eve operations source completion, 2026-09-08: the library contains 68 guides, 748 unique slides, 771 guide-slide instances and 414 cited paths. The new closing page maps all five documents linked from the operations handbook to their distinct safety/privacy, model-quality, platform-evidence, platform-control and continuing SMX-maintenance roles. The source-scoped report now has all ten meaningful units reviewed, no errors and complete: true. The 111.911-second local narration, complete twenty-page guide PDF and dated verification receipt carry the delivery evidence. The global exhaustive-teaching backlog remains open; this increment does not establish live control health, a passing release gate or a completed maintenance run.

Eve release-procedure teaching, 2026-09-08: the merged library contains 68 guides, 747 unique slides, 770 guide-slide instances and 414 cited paths. One new operations page preserves the standard stage, family, journey and Docs Center checks, all five high-risk suite additions, and the separate roles of the current Eve Deep Test and Polish closure and ongoing Eve SMX maintenance loop. That source now has nine reviewed and one open unit. The dated verification receipt records exact source, visual, narration, PDF and browser evidence. This increment does not establish that a particular change passed or was released.

Tara discovery delivery, 2026-09-08: the new twenty-four-slide Tara service discovery, saved items and launch guide follows recommendation reads, configured search pools, card identity, bridge ordering, favorite requests, complete/partial reconciliation, page walks and launch precedence. Native diagrams and worked records accompany 31.6 minutes of narration and a complete PDF. All 722 previous slides and recordings and 67 earlier guide HTML files remain exact. The library now has 68 guides, 746 unique slides, 769 guide-slide instances and 413 cited paths. The receipt retains 26 source cases, 174 final visual checks and focused center/PDF evidence. Earlier counts below are historical checkpoints. Full V1 work remains active.

Tara web search delivery, 2026-09-08: the new sixteen-slide Tara web search and result navigation guide explains local example content, debounce, synonyms, weighted matching, grouped results, highlights, spelling, recent history, storage failure and navigation. Two readable source captures and native diagrams accompany 20.0 minutes of narration and a complete PDF. All 706 previous slides and recordings and 66 earlier guide HTML files remain exact. The current library has 67 guides, 722 unique slides, 745 guide-slide instances and 405 cited paths. The receipt retains 117 final visual checks, nineteen source-component cases and complete focused center/PDF evidence. Earlier counts below describe historical checkpoints. Full V1 work remains active.

Tara catalog and Eve service-level integration, 2026-09-08: the current library contains 66 guides, 706 unique slides, 729 guide-slide instances and 403 cited paths. It includes the complete 22-slide Tara catalog guide and the four incoming Eve service-level slides. All 706 recordings, both manuscripts and every guide HTML file retain their owning delivery bytes. The integration receipt records the current center/PDF checks and precisely reused evidence. Earlier counts below describe their individual delivery checkpoints. Full V1 work remains active.

Tara catalog delivery, 2026-09-08: the new 22-slide Tara practice catalog and records guide follows recommendations into linked practice, content and teacher records, with taxonomy, duration, rights, accessibility, cadence and contract examples. Native diagrams, record specimens and comparisons add 29.0 minutes of narration and a complete PDF. Final review passes 160 visual checks and the complete focused center/PDF checks. All 680 previous slides and recordings and 65 earlier guide HTML files remain exact. Before integration, this delivery contained 66 guides, 702 unique slides, 725 guide-slide instances and 403 cited paths. The receipt records actual review and its limits. Full V1 work remains active: recommendation/search/launch consumers, full taxonomy selection, native callers, companions, mentors, workbenches and other V1 workstreams still need their owning explanation. Human reader/listening acceptance is unperformed.

Eve service-level teaching after Tara web-practice integration, 2026-09-08: the Eve delivery contained 65 guides, 684 unique slides, 707 guide-slide instances and 399 cited paths. Four new operations slides preserve every required latency, routing, effect, confirmation, grounding, safety, provider, continuity, client, evaluation, drift and outcome-cost measure, then bind alerts to a runbook and affected plane. That source now has eight reviewed and two open units. The dated verification receipt records exact source, visual, narration, PDF and browser evidence. This increment does not establish live thresholds or measured service levels.

Tara web practice delivery, 2026-09-08: the new 21-slide Tara practice and the web sitting player guide follows the actual course rows, player controls, timer, text/audio boundaries, start and completion records, reflection storage and later readback. Three focused source-component captures and native diagrams add 27.9 minutes of narration and a complete PDF. Five slides received composition polish; 153 final visual checks and the complete focused center/PDF checks pass. All 659 earlier slides and recordings and 64 earlier guide HTML files are preserved. The library now has 65 guides, 680 unique slides, 703 guide-slide instances and 399 cited paths. The receipt records exactly what was reviewed. Full V1 work remains active, including Tara catalog/recommendation, native callers, companions, mentors and workbenches. Human reader/listening acceptance remains unperformed.

Tara scheduling delivery, 2026-09-08: the new fifteen-slide Tara scheduling and reminders guide follows an evening return through invitation timing, timezone resolution, quiet hours, reminder construction, storage queries and reschedule identity. Worked clocks, decision diagrams and record specimens add 22.3 minutes of narration and a complete PDF. The final review corrected a narrow-screen heading overflow; 111 visual checks and the complete focused center/PDF checks pass. All 644 earlier recordings and 63 earlier guide HTML files are preserved. The library now has 64 guides, 659 unique slides, 682 guide-slide instances and 386 cited paths. The receipt records the exact scope. Full V1 work remains active, including Tara practice/player, companion, mentor and workbench depth. Human reader and normal-speed listening acceptance remain unperformed.

Tara session delivery, 2026-09-08: the new 21-slide Tara ritual sessions and recovery guide explains lifecycle history, completion thresholds, continuation, skip, recovery, projection identity and saved-return evidence through native diagrams and worked cases. It adds 32.2 minutes of narration and a complete PDF. Two older Tara explanations and their tracks are corrected; all 621 other upstream recordings and 61 other guide HTML files remain unchanged. The merged library now has 63 guides, 644 unique slides, 667 guide-slide instances and 386 cited paths. The receipt records 223 visual checks, complete focused center/PDF checks and four reviewed feature units. Full V1 work remains active, including Tara practice selection, player, scheduling, companions, mentors and workbench depth. Human reader and normal-speed listening acceptance remain unperformed.

Eve operational-dependency checkpoint before Tara integration, 2026-09-08: the library contains 62 guides, 623 unique slides, 646 guide-slide instances and 378 cited paths. Three new operations slides preserve every dependency, operational concern and required degraded behavior in the pinned nine-row dependency map. That source now has seven reviewed and three open units. The dated verification receipt records exact source, visual, narration, PDF and browser evidence. This increment does not certify live dependency health or close the exhaustive teaching backlog.

Offline continuity delivery, 2026-09-08: the new twenty-slide Offline reading, updates and queued work guide follows worker activation, reading updates, cache selection, explicit background actions, library retries/replay and session cleanup. Native diagrams keep the two queue implementations and their failure behavior distinct. It adds 30.3 minutes of narration and a complete PDF; all 600 earlier recordings and 61 earlier guide HTML files are preserved. The library now has 62 guides, 620 unique slides, 643 guide-slide instances and 378 cited paths. The offline receipt records 146 visual/accessibility checks, complete focused center/PDF checks, pinned source characterization and four reviewed source-unit assignments. The full V1 program remains active; Tara and the other room guides are next. Human reader and normal-speed listening acceptance remain unperformed.

Eve operating-state teaching, 2026-09-08: the current library contains 61 guides, 600 unique slides, 623 guide-slide instances and 365 cited paths. A new three-slide sequence teaches the complete documented operating graph: classify Healthy, Degraded and Incident; choose ReadOnly, Fallback or Unavailable from proven remaining capability; contain incidents; then reconcile through Recovering before returning Healthy. It assigns the exact pinned top-level operations unit, moving that source to six reviewed and four open units. The dated verification receipt records source, visual, narration, PDF and browser evidence. This increment does not certify a live operating state or close the exhaustive teaching backlog.

Account guide delivery, 2026-09-08: the new seventeen-slide Account, preferences and personal controls guide follows a concrete preference change through editors, payloads, persistence and specialist readbacks. It adds memory, voice, safety, notifications, Telegram, data-rights, connection and billing depth, with 27.0 minutes of new narration and a complete PDF. All 580 earlier recordings and all 60 earlier guide HTML files are preserved. The library now contains 61 guides, 597 unique slides, 620 guide-slide instances and 365 cited paths. The account receipt records the 125-check visual/accessibility matrix, complete focused center checks, exact PDF text and all seven reviewed account-feature units. The full V1 program remains active; offline and room depth are next. Human reader and normal-speed listening acceptance remain unperformed.

V1 foundation revision, 2026-09-08: the twelve-slide Lilith web/PWA guide now has a concrete result case, four distinct launch rooms, labeled shell/account and release relationships, and both update choices. Six affected PDFs and the new recording are delivered; all earlier recordings are preserved. The parallel Eve configuration update is integrated, bringing the library to 60 guides, 580 unique slides, 603 guide-slide instances and 348 cited paths. The foundation receipt records actual review and verification. The full V1 audit remains active; this increment does not close the detailed room, account, workbench, platform or source-unit teaching work.

Eve configuration teaching, 2026-09-08: the current library contains 60 guides, 579 unique slides, 602 guide-slide instances and 348 cited paths. A new operations slide separates the committed configuration-name map, resolved startup bindings, secret material and the evidence required for two kinds of release-affecting change. It assigns the complete pinned Configuration and secrets source unit while retaining five open units in that source. The dated verification receipt records the delivered visual, narration, PDF and browser evidence; this increment does not certify any live environment or close the exhaustive teaching backlog.

Eve design completion, 2026-09-08: all 25 Eve guides / 204 slides now use the field-guide edition. The remaining product-guide repairs add concrete cases, pinned Explorer/Work/Audit imagery, a complete recovery map, an ADR replacement relationship and an executed hypothetical readiness result. Four architecture diagrams now use readable wrapped labels; image-pan keys no longer advance the deck. The library has 348 cited paths; guide/slide counts and spoken scripts are unchanged. Open the Eve route. The complete sequence review, per-slide ledger and verification receipt record what reached the slides. Human reader acceptance and the wider whole-library teaching/design program remain distinct from this delivered Eve pass.

Combined delivery, 2026-09-08: the Eve capability expansion and the parallel V2 rollback-session guide are integrated. The library contains 60 guides, 578 unique slides, 601 guide-slide instances and 347 cited paths. Both additions retain their authored content and narration. The integration receipt records the shared-catalog checks and exact continuity with each verified parent.

Eve product capabilities, 2026-09-07: start with Use Eve, a 12-guide, 94-slide path through actual product workflows. It covers product graphs, coverage and impact analysis, task tracking, discussions and decisions, delivery, operator investigations, studio analysis and actions, member feature audits, and shared member tools. Each slide includes detailed explanations, source excerpts and three review questions. The path adds 132.5 minutes of narration; each guide also has a PDF edition.

The order follows a continuous example: inspect a feature → establish the gap and evidence → capture and prioritize work → discuss alternatives and record a decision → follow execution, verification and delivery. Studio and member chapters apply those distinctions to their own tools. A final exercise asks the reader to reconstruct the evidence and identify unsupported completion claims.

The Eve learning path combines these 12 product guides with the 13 existing architecture guides: 25 guides and 204 slides without exact repetition. Readers who already know the product can use Eve architecture, or its six-guide overview. Stable guide URLs remain available. Before the parallel rollback guide was merged, this checkpoint had 59 guides, 564 unique slides, 587 guide-slide instances and 344 cited paths.

Read the capability teaching and sequencing review, explicit tool/view teaching crosswalk, and verification receipt. New teaching is pinned to 8c27a8d3350fe7484c18585b570f72a561090540; older architecture chapters retain their own source dates. The crosswalk covers all 90 declared assistant tools, 7 executing-agent MCP operations and 31 studio views at that revision. It is a bounded inventory of those registries, not a claim that every deployment exposes them or that the whole monorepo's teaching is complete.

Previous Eve learning sequence, 2026-09-07: the architecture sequence pairs each introduction with its detail: purpose/invocation, context/evidence, authority/safety, execution/recovery, models/evaluation and operations/change, then the dated implementation and final course review. Its 13 guides contain 110 slides without exact repetition and about 155 minutes of narration. The six-guide overview follows the same conceptual order in 60 slides and about 80 minutes. Route links retain a shared guide when switching; Next/Previous stay within the chosen route.

Worked cases now precede the detailed mechanisms. One draft-revision example connects the chapters and ends with changed access, a competing edit and a lost approval reply. Seven recordings follow the revised wording. The parallel rollback checkpoint below had 484 unique slides and 48 guide URLs, with 507 guide-slide instances and 311 cited paths before the capability expansion was merged. Read the editorial review and verification receipt.

V2 rollback-session integration, 2026-09-07: the fourteen-slide V2: correcting a predicted frame guide traces prediction, confirmation, replay, recovery and the next live result through one worked tick. It adds 1,237.964 seconds of narration. Five added native cases bring the explicitly adapted local UE host to 25 passing cases; this does not establish an unchanged-pin build or live-match acceptance. Two complete architecture sections now have reviewed teaching assignments. See the integration receipt for the final verification, retained failures, optical review and source limits. Normal-speed listening, willing-reader comprehension and the exhaustive presentation objective remain incomplete.

Previous Eve expansion, 2026-09-07: seven detailed Eve guides added 49 slides and 4,298.013 seconds (71.6 minutes) of narration. That checkpoint had 47 guides, 470 unique slides, 496 guide-slide instances and 308 distinct cited source paths. Eve's detailed routes cover invocation, execution, memory, safety, model evaluation, operations and recent implementation. Each slide includes an explanation, source excerpts and questions; the guides also have prerequisites and PDF editions. Start with the guide map, or read the teaching route and reader exercises.

Architecture teaching retains source revision 1ceae52c7896a59ac74a4429d410f3218f0b91c6. The current-runtime guide separately pins 6c3186d2a4bac18f17acdbb63b3177759f32d6df, including authority, isolation, retained security measurements, speech defaults, page capture and reply inspection. Each source panel names the revision it actually contains. Later implementation evidence cannot satisfy teaching assignments in the older inventory. The guide states its remaining implementation and live-evidence limits explicitly.

The historical Eve integration receipt records browser, source, PDF and narration checks, visual reviews and continuity with the previous library. That edition had 13 Eve guides and 113 slide instances, totaling about 156 minutes. Human listening and reader trials, and the library-wide exhaustive teaching objective, remain separately scoped.

This edition includes the shared table typography and print repairs: authored header case, larger headers, intact number/unit expressions and complete printed rows. It also includes the short-viewport navigation repair, preserving complete guide titles and access to navigation/details at high zoom. The reviewed V2 network-quality teaching assignment is retained.

Historical machine-transfer checkpoint, 2026-09-06: work is intentionally incomplete. Resume from the exhaustive continuation checklist and the checkpoint record. The catalog at handoff had 38 guides and 380 unique slides; 64 recordings used the new sentence timing, while 297 are stale and 19 are missing. The player marks unfinished narration explicitly. The completed-phase description below is historical.

Previous V2 connection-quality integration, 2026-09-07: the library has 40 guides, 421 unique slides, 447 guide-slide instances and 287 cited sources. The twelve-slide guide follows measurements through handshake, pressure, fallback, validation, score and diagnostic metadata, separating local records from actual match or operations effects. Its Netcode route follows product promise and contracts. All 421 recordings are current, totaling 38,115.121 unique seconds and 40,192.443 route seconds; the guide adds 1,190.383 seconds. All 409 previous recordings and speech scripts and 39 previous guide HTML files are preserved. The full 40-guide center, all 40 PDFs, complete 421-slide bank, new standalone guide and focused playback checks pass with observed exit zero. The integration receipt binds exact evidence and 177 model-inspected images, keeping native fixture continuity separate from new execution. Mobile number/unit cohesion and small page-fit prose-table headers remain explicit defects. Normal-speed listening, real reader review, source-unit assignments, full craft acceptance and the exhaustive objective remain incomplete.

Previous V2 contracts integration, 2026-09-07: the library had 39 guides, 409 unique slides, 435 guide-slide instances and 280 cited sources. The new eighteen-slide guide follows reference conventions, distinguishes executable value schemas from artifact checks, traces floating-point build/cook policy and reproduces a pinned gRPC metadata freshness failure. Its guide brief records the source boundaries and all eight craft requirements; no Unreal build or live RPC acceptance is claimed. All 409 recordings pass fingerprint, file/hash, duration, decode and encoded-pause checks, totaling 36,924.738 seconds of unique audio and 39,002.060 seconds across the guide routes. The 38 previous guide HTML files and all 391 previous recordings are preserved exactly. All 39 PDF exports and the complete center report pass, as do the complete 409-slide bank and shared-table/companion regressions. The integration receipt retains exact report/artifact hashes, 157 reviewed images and the unsuccessful attempts that preceded the final checks. Normal-speed listening, real reader review, the accepted design benchmark and the exhaustive TODO objective remain incomplete.

Previous source and narration checkpoint, 2026-09-07: the library had 38 guides, 391 unique slides and 253 cited sources. All 391 recordings pass the full fingerprint, file/hash, duration, decode and encoded-pause check, totaling 34,841.439 seconds of unique audio. Following all guides totals 36,918.761 seconds because shared context plays again where reused. All 380 unaffected recordings from the completed 388-track queue—including the original 177 current recordings—are preserved exactly. Eight Agentic Studio corrections and three execution detail slides are applied; the guide brief separates local checks, attempted work and external effects. The full 391-slide standalone suite and 38-guide center suite pass, including actual playback, all 38 PDFs, 834 embedded captures and 76 guide audio boundaries. Both focused V2 standalone suites also pass. See the automated checkpoint for exact scope and visual findings at that revision. The subsequent companion-label repair shortens two visible row names, preserves all 391 recordings and reruns the complete affected standalone and focused embedded checks. The earlier full-bank reports remain historical rather than being replaced by focused results. Normal-speed listening, real reader review, final composition acceptance and the exhaustive expansion remain incomplete.

Earlier Linux checkpoint, 2026-09-07: 177 recordings passed current-audio verification; 191 were stale and 20 were missing. The library then had 38 guides, 388 unique slides and 238 cited sources. The unpublished V2 contracts manuscript has expanded to 16 source-reviewed slides with isolated draft checks; the companion explanation now distinguishes match authority from scoped API writes. See the draft record and companion/teaching review. The Nyx/contracts review records Nyx's complete current-audio standalone check and the contracts draft's sixteen-slide visual/editorial pass, including all PDF pages. The narration rebuild, contracts-guide integration and full expansion remain incomplete. The Nisaba follow-up records the next seven regenerated tracks and the source-review findings. The opening Eve follow-up adds 20 current recordings, replaces three corrected explanations' audio and backfills five reviewed teaching units. Orientation and the six Eve guides now have complete audio; the global rebuild and normal-speed listening remain open. The member follow-up adds nine current recordings, corrects Tara clamping and Arete check-in explanations, and records two further reviewed teaching units. V1 web/PWA, Tara and Arete now have complete audio; their learning map retains the remaining source detail and additional pinned-code findings. The shared architecture follow-up adds 20 current recordings and two reviewed units. Contracts/ownership/data and events/jobs/discovery now have complete audio. Corrected explanations cover partial-failure validation, event-bus recovery boundaries and the curation package inventory; the learning map retains the remaining source depth. The Sophia follow-up adds eight current recordings and four reviewed units. Sophia now has complete audio. The extractive explanation includes title fallback and exact count semantics; the synthesis examples distinguish identifier cleanup, retained model prose, abstention and exception fallback. The Sophia learning map records the remaining implementation and teaching depth. The Iris follow-up adds two focused slides, completes seven previously pending recordings, narrates the two new slides and replaces the corrected shared Eve memory recording. Six more source units have reviewed assignments. Iris now has complete audio; its explanations separate write planning from recall, correct recency decay and distinguish local consent/inspection records from integrated rights enforcement. The Iris learning map retains the remaining source depth and integration boundaries. Global narration and normal-speed listening remain incomplete.

The content-led composition pilot is now in progress. Its initial treatments replace the web/PWA opening's numbered columns with independent question/evidence pairs and replace member-day's compulsory-looking room chain with optional activities, a skip path and an explicit return. Shared use in Psyche/Lilith is retained. Per-guide art direction and the reader protocol record the wider pilot and missing human evidence; these are not accepted benchmarks or a completed migration. The Psyche learning map records four additional mechanism slides, precise pinned-code boundaries and five more reviewed teaching units. Psyche now has complete current narration; full pilot adoption and normal-speed listening remain incomplete.

The initial composition verification records both treatments, the current source corrections, 210 passing unit tests, full web/PWA and draft Psyche standalone checks, and the current 38-guide center run. Its model review covers 165 images across sixteen unique slides, including before/after and actual-size variants. Open table, decision, typography and reader-review findings remain explicit; this is not full pilot acceptance.

The priority-decision follow-up makes Psyche's actual first-supplied trigger selection visible, with separate validation-error and no-signal outcomes. Nine recordings complete its fifteen-slide guide at 1,868.740 seconds. The full Psyche and web/PWA standalone suites pass with actual audio; a compact playback overflow found by that deeper check was corrected and added to the 49-capture pilot matrix. All eleven web/PWA slide briefs now describe the planned narrative, relationships and transitions, without claiming their remaining treatments have been implemented. The global narration backlog, typography/quantitative work, remaining pilot migration and real reader review remain open. Its complete center run verifies all 38 PDFs and 36 desktop/mobile playback boundaries across 18 ready guides. Both complete contact sheets were inspected; repetitive legacy compositions remain migration work. Its room-maturity desktop cell-separation finding is retracted: the baseline image is byte-identical and actual text ranges show 195.984375px of separation. No desktop padding fix was warranted or made.

The table-continuity follow-up adds exact typed latency targets, pinned export provenance and a visible missing-configuration legend. Narrow tables keep row names alongside the column being read; numeric values align right, and non-overflowing tables no longer display an unnecessary scroll hint. The table brief records the source-backed choice to retain a table, its viewing scope and neutral reader tasks. This is another pilot candidate, not a completed chart system or accepted benchmark. Its verification record includes 102 Python and 137 Node tests, 34 focused table captures, both complete standalone guides and all 38 center guides/PDFs. All 91 table instances pass desktop/mobile text/identity checks. Current audio is unchanged; the global backlog, wider pilot and real reader evidence remain open.

The ownership follow-up adds source-backed Tara read handoffs after the conceptual architecture map. Native responsibility lanes become explicitly named exchanges on narrow screens. The explanation separates successful orchestration from rejection, authentication and deployed effects. Its 173.323-second recording brings current audio to 16,007.673 seconds; all 177 current tracks pass fresh decode/pause checks. The twelve-slide architecture suite, 64-capture composition matrix and full 38-guide center/PDF checks pass, alongside 253 Python/Node tests. The brief and review ledger keep the remaining legacy treatments, typography and reader evidence explicit. This is another pilot candidate, not full pilot or library acceptance.

The annotated-source follow-up replaces the PWA lifecycle arrows with an exact source excerpt and focused annotations. The waiting-worker helper's local return is distinct from worker activation, page refresh or server acknowledgement. Responsive code wrapping preserves exact characters and provenance; installation/native and privacy context remain in the explanation. All 264 Python/Node tests, the complete web/PWA standalone suite, 77 focused composition captures and all 38 center guides/PDFs pass. The replacement recording brings current audio to 16,103.359 seconds across 177 tracks, all freshly decoded and pause-verified; 211 tracks remain pending. The brief and scoped review ledger keep full-guide migration, typography, normal-speed listening and reader acceptance open.

Open the presentation center to browse the current 48-guide catalog. Its original Eve/V1 subset contains 35 guides and 349 unique slides, preserving all 244 foundation slides and adding 105 topic-specific explanations, worked cases and failure analyses. Seven detailed Eve guides, the portfolio overview and five V2 guides extend that subset; they do not establish comprehensive V2–V10 coverage.

Use the collapsible hierarchy to choose a guide. Guide details shows its purpose, recommended preparation, slide count and narration time. Previous guide and Next guide follow the reading order. The guide map lists the hierarchy and listening times.

  • Contents searches the selected guide's slides and explanatory material.
  • Explain opens detailed notes, questions and embedded source excerpts.
  • Script shows the complete narration text and questions covered.
  • Narrate plays local audio through the guide, with pause, seek, speed and stop controls. Changing guides or opening a center dialog pauses playback.
  • PDF opens the selected guide's visual-slide export. Open separately opens its standalone HTML presentation.
  • Arrow keys navigate slides; Home and End reach the first and last slide. ? lists the remaining keyboard controls.

Times are measured from current MP3s at 1× and rounded up to the minute. Every parent section includes its descendant guides. Shared context is deliberately repeated where a guide needs it to stand alone, so section totals count that listening time in each guide. Stale audio is excluded from playback and completed duration totals until regenerated.

Copy the complete presentation-center directory to retain offline navigation, audio and embedded excerpts. Open source file links require the repository checkout. A static HTTP server can serve the same directory.

Tracks#

Every guide in this library belongs to exactly one track, and a track is a numbered sequence of chapters rather than a folder of related pages. The distinction is what the reader gets: a chapter strip on every slide saying which track it belongs to and which chapter of how many, a footer naming both, and a close that bridges to the next chapter by name. A guide's position is not a label written on it — it is its index among the guides declaring that track in catalog-source.json, so a chapter cannot claim a number the catalog disagrees with.

The sidebar is one folder per track, and the build refuses any other shape: a track split across two folders would read as two things, and two tracks sharing one folder would hide the chapter order. Folders are ordered by the order the tracks are declared, not by the order guides appear in the catalog file, because that file has to list some chapters out of track order to keep every guide's recommended preparation ahead of it.

The seventeen tracks, in reading order:

Section Tracks
Start here start-here
Eve use-eve, how-eve-works
Oshun V1 meet-lilith, tara-find-a-practice, tara-practise, tara-continue, tara-native-offline, other-rooms, shared-systems, creation, governance-commerce, native-apps, veritas-metis
V2 v2-orientation, v2-netcode
Delivery and release delivery-release

Release scope (V1.0, V1.1, V1.2) is a property of a chapter, not a place to file it. The release folders that used to split one product story across three sections were retired on 13 September 2026.

Every track also has a reading route listing exactly its chapters in chapter order, and library-course is the whole library in preparation order — the only ordering in which no chapter arrives before something it depends on. Three Tara tracks interleave there rather than running one after another, because Tara · practise chapter four needs two chapters of Tara · continue, and Tara · continue closes on the native player.

Scope and evidence#

The original Eve/V1 phase reviewed 191 source files at commit 1ceae52c7896a59ac74a4429d410f3218f0b91c6, with the presentation review dated 2026-09-06. Excerpts come from that exact Git snapshot. Opening a source file in the checkout may show a newer revision.

The current source and guide coverage map connects 311 cited source files and their slides to the presentations. Citation coverage is not complete section-level teaching review; that stricter evidence is recorded in the teaching report. Foundation coverage preserves the original slide identifiers and verified foundation HTML hash; the builder refuses to omit one. Detailed coverage records source hashes, slide titles and references. Each guide also has a coverage file in decks/.

The guides distinguish implementation, runtime wiring, configuration, proposed design and demonstrated acceptance. Worked examples are explanatory scenarios, not invented production incidents or measurements. Product release claims remain governed by the pinned sources. This library's checks verify the presentation artifacts and behavior.

Verification details describe the automated checks, visual review and machine-readable reports for this Eve/V1 library.

The comprehensive expansion tracks the subsequent V1–V10, Docs Center, Eve integration and Domains work. Its section-level inventory is separate from the delivered guide catalog and does not claim completed teaching coverage.

Pinned repository discovery additionally accounts for all 140,123 tracked Git entries, including code, workflows, configuration and assets outside the documentation inventory. Its file and declared-manifest projection exposes further coverage work; it does not claim semantic-unit teaching, an effective workspace graph or final Domains acceptance.

Workflow declaration units begin the non-Markdown semantic inventory: all 106 pinned workflows and two action definitions yield 3,718 still-unassigned units. Their separate teaching gate binds exact source context and explanatory slides; parsing is not teaching or evidence of successful CI execution.

The Agentic Studio application applied and narrated the recovery corrections: checkpoint matching does not verify the whole envelope or enforce the recorded resume budget. The earlier source review is historical preparation, not a current pending-application claim. The deeper agentic/workflow coverage, normal-speed listening and reader acceptance remain open.

Narration#

Audio uses the stock Kokoro af_heart voice at 0.95 synthesis speed, with no voice cloning. The renderer pins Kokoro/Misaki 0.9.4 and model revision f3ff3571791e39611d31c381e3a41a3af07b4987 of hexgrad/Kokoro-82M. MP3s are mono, 24 kHz and 64 kbps, with normalized loudness.

Oshun, OSHUN and Ọṣun use the requested oh-shuhn pronunciation, including canonically decomposed Unicode spellings. Explicit Misaki phonemes ˈOʃən affect speech only; authored spelling is preserved. Tests check both normalization and the actual speech frontend.

Headings, subtitles, explanatory paragraphs and takeaways retain separate speech blocks. Complete sentences are synthesized individually, with 0.40 seconds of inserted silence between sentences, 0.85 after a heading and 0.70 between other blocks. The recording retains short natural breath margins as well. Versions, decimal numbers, paths, initials and common abbreviations stay together. The Script panel displays the same paragraph structure.

The narration manifest records duration, bytes, SHA-256, content/settings fingerprint, rendering device and sentence timing for every track. Duration is measured from decoded playable samples; MP3 container duration can include encoder delay and padding on some FFmpeg versions. Verification decodes the actual MP3 and checks that every inserted pause survived encoding. Speech grouping and pause settings participate in freshness checks; playback URLs include the audio hash so regenerated speech gets a new cache entry. The narration script is generated from reviewed content.

Rebuilding and checking#

Run commands from the repository root. Use Python 3.11 or newer, FFmpeg/ffprobe, Poppler (pdftotext and pdfinfo), repository Node dependencies and installed Chrome. The tested Playwright version is 1.60.0.

sh
python3.11 -m venv .venv-presentations
. .venv-presentations/bin/activate
python -m pip install -r tools/presentations/requirements.txt
python tools/presentations/build-eve-oshun.py --preview

For narration, install the speech dependencies and English language model. The tested language model is en_core_web_sm 3.8.0. Weights and the stock voice download on first use and then use the local cache.

sh
python -m pip install -r tools/presentations/requirements-narration.txt
python -m spacy download en_core_web_sm
python tools/presentations/render-eve-oshun-narration.py --batch-size 6
python tools/presentations/build-eve-oshun.py --preview

The default device is CPU with one thread. --device mps --threads 1 uses the tested Apple GPU path where available. Batches run sequentially in fresh processes, resume missing or stale tracks, stop on resource pressure or failure, and finish with full fingerprint, hash, duration and decode verification. Run one narrator at a time.

On Linux, install CPU-only PyTorch from the official CPU wheel index to avoid unneeded accelerator packages. The destination environment uses Python 3.12.3, the pinned requirements and en_core_web_sm 3.8.0:

sh
python -m pip install -r tools/presentations/requirements-narration.txt --extra-index-url https://download.pytorch.org/whl/cpu
python -m pip install https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl

Repository Playwright can also use its installed Chromium with CHROME_CHANNEL=chromium. Record the browser version in verification evidence; the destination browser differs from the historical Chrome run.

After content and audio are stable, run the complete checks:

sh
python tools/presentations/build-eve-oshun.py --check --preview
python tools/presentations/render-eve-oshun-narration.py --check
python -m unittest discover -s tools/presentations/tests -p 'test_*.py'
node --test tools/presentations/tests/*.test.mjs
ruff check tools/presentations
node_modules/.bin/eslint --config tools/presentations/eslint.config.mjs docs/presentations/presentation-center/*.js tools/presentations/*.mjs tools/presentations/tests/*.mjs
node_modules/.bin/prettier --check docs/presentations/presentation-center tools/presentations
python tools/presentations/run-supervised.py node tools/presentations/tests/eve-oshun-deck.mjs
python tools/presentations/run-supervised.py node tools/presentations/tests/presentation-center.mjs

A wiring slide does not describe its own ports. authoring/graph-fixtures/ holds the port truth for each workflow a slide draws, written by tools/presentations/graph-fixture.mjs out of the rendered graph and the worker image's own class snapshot; the build then refuses any class, port, index or type on a slide that the fixture does not have. Regenerate one after a graph or an image rebuild, and read a retired graph at a revision where it and its classes still existed:

sh
node tools/presentations/graph-fixture.mjs --workflow chroma-txt2img --variant square_1024
node tools/presentations/graph-fixture.mjs --workflow sam3-video-track --variant text \
  --revision <sha> --retired-item 'ComfyUI-SAM3 pack' --retired-date '14 September 2026' \
  --out docs/presentations/presentation-center/authoring/graph-fixtures/sam3-video-track-retired.json

A measured panel does not carry its own numbers either. authoring/measurements/ holds a request per panel — for each figure, the evidence file and the exact place in it: a JSON pointer, or a named row and column of a named table in a named section, or a pattern over one section's prose — and tools/presentations/measurement-extract.py reads them and writes the panel's points beside the request. A figure whose row is gone, whose pattern matches nothing, or whose pattern matches twice stops the extraction; a RunPod dollar figure must say whether it is a ledger bound or a settled balance, and the emitted point says so. A threshold-panel names its request and the build refuses a point that is not the extracted one.

sh
python tools/presentations/measurement-extract.py --request aligner-onsets
python tools/presentations/measurement-extract.py --request aligner-onsets --check

Follow repository host-resource checks before expensive verification. Run browser and narration jobs separately. The supervisor samples memory every 30 seconds and stops its owned process group below 2 GiB available memory. Narration also enforces disk reserves and model-load headroom.

A new guide can receive the complete focused center checks with presentation-center.mjs --guides <guide-id> --base-revision <40-character-commit>. This mode requires all unselected guide HTML and shared UI files to match the immutable commit. Its report distinguishes file continuity from prior guide acceptance. Omit --base-revision to require the existing ordered chain of passing baseline reports. A shared UI change requires broader coverage.

The ignored .qa-preview/ whole-bank fixture exists only for regression tests; the delivered reading routes are the focused guides. The center's full test creates and validates each guide PDF. OSHUN_DECK_QA_DIR and OSHUN_CENTER_QA_DIR override the temporary report and screenshot directories. --draft, --smoke and partial-check flags support authoring, but do not replace the complete checks above.

During the narration rebuild, presentation-center.mjs --draft --ready-audio checks every guide's layout and PDF, plus actual embedded audio boundaries for each fully narrated guide. It reports the tested and skipped audio scopes; this partial mode is not the final narrated release gate. Complete center runs also save and hash every embedded desktop/mobile initial-viewport capture in embeddedSlideCaptures. Those images support editorial review; they do not replace full-height standalone mobile/table-end or PDF inspection.

Unpublished manuscripts in drafts/ can be reviewed without adding guides, slides or audio to the delivered catalog. They must declare the same immutable sourceRevision as the library. The builder renders their actual layouts and source excerpts into an ignored, isolated fixture:

sh
python tools/presentations/build-eve-oshun.py --draft v2-contracts
python tools/presentations/build-eve-oshun.py --draft v2-contracts --check
python tools/presentations/run-supervised.py node tools/presentations/tests/eve-oshun-deck.mjs --draft-id v2-contracts --draft

Draft checks cover the rendered manuscript; narration, catalog placement, teaching assignments and final publication require their subsequent checks.

A change Eve proposes is a different kind of draft: drafts/eve-<changeId>.json, its change id a UUID, holds complete replacements for slides that already exist with the digest of each slide it replaces and who proposed it (authoring/eve-change-drafts.md). It is a working file git ignores, and tools/presentations/eve_change.py is how the BFF checks and shows it. Each replacement is held to its chapter file's rules and read at its chapter's own source pin — which a manuscript draft is not — before every validator of a draft build runs on it, one slide at a time. Every invocation prints one JSON document; the exit status is non-zero only for an internal error (1) or a malformed invocation (2):

sh
python tools/presentations/eve_change.py validate --draft docs/presentations/presentation-center/drafts/eve-<changeId>.json
python tools/presentations/eve_change.py preview --draft docs/presentations/presentation-center/drafts/eve-<changeId>.json

validate answers {ok, findings}, each finding {slideId, rule, message} (slideId is null for the draft as a whole). preview renders .qa-draft-eve-<changeId>/ only when there are no findings, answering its deckPath relative to this directory and the slideIds in it; a refused draft has its earlier preview removed.

Edit content/*.json, diagrams.json, catalog-source.json, meta.json, or the shared CSS/JavaScript, then rebuild. Do not edit generated HTML, coverage, scripts, catalog, guide map or audio metadata directly. Changing the source revision requires reviewing affected claims and regenerating their evidence.