zonggong and multica-agent
81d50f28af
HEL-868: fixed 13-call real A/B retest executed in one bounded round per rework860 _retest_plan under the original '同意测试' authorization after manager HEL-867 review lifted the stop gate - criteria/fixtures/orchestration untouched at e06dcaf (driver only captures per-call raw input/sent-context/answers and writes per-scenario outputs, never overwriting ab_scenarios.json); preflight zero-embed zero-network audit861_reuse868 + audit867_reuse868 both exit 0 with prior evidence and ledgers unchanged; 13/13 calls sent HTTP 200 (ADD1-5 anchored real extraction + QA1-8), real ledger continued on a SQLite-consistent backup of the original 26-row ledger (prefix line digest 03f92557 identical, original read-only preserved) now 39/60, embed ledger 458->498/500 (+40 dense, pre-computed debit guard held), usage 163041 tokens recorded per call; honest per-scenario results: S1/S4/S5/S8/S9 pass, S2/S3 mem0 side and S7 fail fail-closed because base-group batch-anchored infer hits carry the unshared t1 companion row in the group anchor and companion_unshared rejects them at every exit (zero leak markers in all sent contexts - the gate holds; row-level provenance for batch extractions is our adaptation gap, not visible to offline row-anchored fake payloads), S3 retrieval layer strictly better re-confirmed (11:11 target hits vs baseline 0:0) but model-use verdict fails without the gated content, S6 orchestration/status-in-block/unresolved-contrast all pass while both real answers are descriptive '资料里说...' unsupported by the pre-declared bounded grammar and honestly fail closed; no rerun, no criteria relaxation, no debug requests, no merge, no deploy; dual-target requirement checks 4/4 pass with handoff-HEL-868.json
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-26 03:49:33 +08:00
zonggong and multica-agent
e06dcaf889
HEL-867 handoff: deliverable/acceptance/deferred/verification JSON; audit867_prefix reproduced at 5e90136 worktree (manager minimal unresolved positive 'you haven't received the result yet' + I/omitted subject + the notification family + 30 negation-aux x received x object cells + 3 overlapping receive-matrix rows all mis-rejected through the same real s6_result while parse open+bound and affirms_promise_state true - mis-rejection in the overall predicate layer) + audit867_postfix at code commit 454e54c (all previously mis-rejected correct unresolved forms pass; 120-row grammar x predicate matrix and manager receive matrix match expectations; double-phase negatives - false resolution clauses incl. I have received the notification, mixed polarity, maybe/foreign object/question/conditional, resolved side says open - all stay failed; resolved-side positives incl. EN recipient-subject received forms kept passing) + manager original review866.py rerun 740/740 exit 0 + audit861_reuse867 full rerun (8 share-gate calls all supplied, t1 unshared/t4 unknown companion raw text never enters sent context, S8/S9 recovery exits, unresolved-block self-consistency, anchor negatives no regression); per-case flip self-check proves exit code depends on every positive and negative; zero-embed zero-network, ledger 458/500 read-only unchanged with identical line digest 8037cbfb (word-surface 160, 181 rows), prior evidence hashes untouched, real 26/60 and 13-request retest plan frozen; dual-target requirement checks 4/4 pass vs origin/main and origin/agent/agent/de8874a3803b with/without handoff
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-26 03:35:21 +08:00
zonggong and multica-agent
5e90136f90
HEL-866 handoff: deliverable/acceptance/deferred/verification JSON; audit866_prefix reproduced at 5ebe407 worktree (manager six receive/fulfill person-object wrong-answer groups - resolved side fixed to canonical positive, only unresolved side replaced - all pass=true; per-class subject x post-verb-slot matrix person cells incl. recipient-subject 'I haven't received me yet' reading all reproduced) + audit866_postfix at code commit cf3423d (all six plus person-object matrix cells and structural variants judged fail through the same real s6_result; canonical positives incl. 我还没有收到, haven't received it yet three readings, 还没兑现 omission, topic form and tell-with-receiver+object all kept; 140 role combos and audit861-865 held S6/S2/S3 sets unchanged) + audit861_reuse866 full rerun (8 share-gate calls all supplied, t1 unshared/t4 unknown companion raw text never enters sent context, S8/S9 recovery exits, unresolved-block self-consistency, anchor negatives no regression); per-case flip self-check proves exit code depends on every positive and negative; zero-embed zero-network, ledger 458/500 read-only unchanged with identical line digest (word-surface 160, 181 rows), prior evidence hashes untouched, real 26/60 and 13-request retest plan frozen; dual-target requirement checks 4/4 pass vs origin/main and origin/agent/agent/de8874a3803b with/without handoff
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-26 03:15:06 +08:00
zonggong and multica-agent
5ebe407d3f
HEL-865 handoff: deliverable/acceptance/deferred/verification JSON; audit865_prefix reproduced at 070f4fd worktree (manager eight role-crossed wrong-answer groups - each replacing only one side with the other side the canonical positive - all pass=true) + audit865_postfix at code commit c0cb540 (all eight judged fail through the same real s6_result; structural variants incl. other pronouns/other promise verb/EN her-us-we-I/mixed multi-promise clauses all fail, both-period negatives honestly kept; omission-inheritance positives incl. wo-hai-mei-you-shou-dao all kept) + audit861_reuse865 full rerun (share gates/real exits/S8/S9/unresolved-block self-consistency/anchor negatives no regression); per-case flip self-check proves exit code depends on every positive and negative; zero-embed zero-network, ledger 458/500 read-only unchanged with identical line digest (word-surface 160, 181 rows), prior evidence hashes untouched, real 26/60 and 13-request retest plan frozen; dual-target requirement checks 4/4 pass vs origin/main and origin/agent/agent/de8874a3803b with/without handoff
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-26 02:56:16 +08:00
zonggong and multica-agent
070f4fd89b
HEL-864 handoff: deliverable/acceptance/deferred/verification JSON; audit864_prefix reproduced at 7aa9280 worktree (manager seven wrong-answer groups plus seven unresolved-side mirrors all pass=true) + audit864_postfix at code commit c65de00 (all fourteen judged fail through the same real s6_result - full-grammar whole-answer parse: declarative mood gate + every clause fully consumed as promise/closed/open structure; positives, HEL-862 four groups, HEL-863 three groups, audit861 held sets, S2/S3 no regression; EN equally verified 3 positives pass 6 negatives fail, old-code EN positive failure honestly recorded) + audit861_reuse864 full rerun (share gates/real exits/S8/S9/unresolved-block self-consistency/anchor negatives no regression); per-case flip self-check proves exit code depends on every positive and negative; zero-embed zero-network, ledger 458/500 read-only unchanged with identical line digest (word-surface 160, 181 rows), prior evidence hashes untouched, real 26/60 and 13-request retest plan frozen; dual-target requirement checks 4/4 pass vs origin/main and origin/agent/agent/de8874a3803b with/without handoff
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-26 02:30:54 +08:00
zonggong and multica-agent
7aa928025b
HEL-863 handoff: deliverable/acceptance/deferred/verification JSON; audit863_prefix reproduced at 6859696 worktree (manager three new wrong-answer groups all pass=true) + audit863_postfix at code commit fcda71e (all three judged fail through same real s6_result - negated tell action and same-clause object mis-binding fail at promise binding layer, state bound to medical result fails at closed-state binding layer; positives, HEL-862 four groups, audit861 held sets, S2/S3 no regression; per-case flip self-check proves exit code depends on every positive and negative) + audit861_reuse863 full rerun (share gates/real exits/S8/S9/unresolved-block self-consistency/anchor negatives no regression); zero-embed zero-network, ledger 458/500 read-only unchanged (word-surface 160, 181 rows), prior evidence hashes untouched, real 26/60 and 13-request retest plan frozen; dual-target requirement checks 4/4 pass vs origin/main and origin/agent/agent/de8874a3803b with/without handoff
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-26 02:08:47 +08:00
zonggong and multica-agent
6859696075
HEL-862 handoff: deliverable/acceptance/deferred/verification JSON; audit862_prefix reproduced at a5ef23f worktree (manager four wrong-answer groups all pass=true) + audit862_postfix at code commit 60cd7fd (all four judged fail through same real s6_result, positives kept, per-case flip self-check proves exit code depends on every positive and negative) + audit861_reuse862 full rerun (share gates/real exits/S8/S9/held criteria no regression); zero-embed zero-network, ledger 458/500 read-only unchanged, prior evidence hashes untouched; remote delivery fix noted in README (pending push)
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-26 01:40:57 +08:00
zonggong and multica-agent
a5ef23f5b5
HEL-861 handoff: deliverable/acceptance/deferred/verification JSON; audit861_prefix reproduced at 22472e4 worktree + audit861_postfix regenerated at final code commit efaa3c2 (zero-embed, zero-network, ledger 458/500 read-only unchanged, prior evidence hashes untouched); dual-target requirement checks pass vs origin/main and origin/agent/agent/de8874a3803b with handoff (4/4)
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-26 01:21:39 +08:00
zonggong and multica-agent
22472e4b92
HEL-860 handoff: deliverable/acceptance/deferred/verification JSON; audit860_postfix regenerated at final commit 6595153 (zero-embed); dual-target requirement checks pass vs origin/main and origin/agent/agent/de8874a3803b with handoff (4/4)
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-26 00:50:04 +08:00
zonggong and multica-agent
9f3e6a33c7
HEL-859 evidence: pre/post negative audit (prefix reproduces all manager-audit bypasses on 892d0d2, postfix @192d959 all rejected via real exits with same-turn user positive kept), full offline suite rework859_offline.json 22/22 exit 0, README revision record with old/new table, handoff HEL-859; dual-target requirement checks pass vs origin/main and origin/agent/agent/de8874a3803b; new evidence independently named, run1/run2 and 26/60 real ledger untouched
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-26 00:19:27 +08:00
zonggong and multica-agent
892d0d2e30
HEL-858: rework per manager independent review - fixture (turn,role) integrity gate, spoken-text share bridge with partial/missing negatives + full restored P1-P5/F1-F8, known-id S4/S6 orchestration with readback and post-update re-retrieval, S7 anchor chain (input fingerprint) with wrong/unknown-source rejection, card-level persistent embed ledger (history rebuilt <=100), _flat/exit-code fixes; zero real model calls, run1/run2 evidence and 26/60 ledger untouched
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-25 23:53:10 +08:00
zonggong and multica-agent
e31ae2d946
HEL-857: approved Mem0 isolation spike - zero-model gates all pass, A/B synthetic scenarios within 26/60 real-call budget
...
- Fixed mem0 source commit 2c81af3 (2.2.1) in isolated venv, qdrant embedded + fastembed local zh embeddings (95.3MB, within 500MB cap)
- Gate0 transport-level persistent debit ledger: 61st call blocked pre-send, failures count, cross-process persistence, retries disabled+counted (fake transport, zero network)
- Gate1 qdrant embedded checks: keyword_search functional (Chinese segmentation gap recorded honestly), restart subprocess, clean-copy restore, no telemetry collections
- Gate2 privacy with stub LLM: P1-P5 zero leak, first-share timing F1-F6 (failed/cancel/unconfirmed no migration, ack+judged migrates told content with anchors, duplicate receipt idempotent), full backup incl. unshared internal memories restores clean
- A/B same-material same-criteria: Mem0 paraphrase recall strictly better than current lexical path (S3, model answers in Chinese), S1-S9 all pass, no regression
- Headline findings: Chinese input extracted as English memories (default upstream prompt), BM25 lexical channel inert for Chinese, ADD-only infer confirmed with our update orchestration, custom metadata needs direct payload read
- 26/60 real outbound via persistent ledger (incl. one parse-failure retry), usage/latency per row; embeddings 28/500; HEL-835 quota untouched
- Experiment branch only: no merge to main/product, no deploy, no real-profile access; handoff JSON + dual-base requirement checks pass
Co-authored-by: multica-agent <github@multica.ai >
2026-10-25 23:19:26 +08:00
zonggong and multica-agent
bb9cbe915e
HEL-847 v4: Mem0 capability corrections per manager review - additive-only infer, backend filter/BM25 facts, pre-isolation privacy design, concrete spike spec
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-25 22:23:53 +08:00
zonggong and multica-agent
800d3b75b6
HEL-847 v3: GOV-006 reweighing - Mem0 embedded SDK as primary candidate, 8-mechanism adaptation matrix
...
- Bounded source review of mem0ai/mem0 @2c81af3 (embedded lib, Apache-2.0,
upstream-maintained extract/consolidate/hybrid-search; SQLite history)
- Zep CE screened out (4-container stack, legacy/docker-compose.ce.yaml:5-71)
- 8-mechanism matrix from discussion takeaways: requirement/current/candidate/
thin-adapter/to-verify per mechanism
- Recommendation shifts from v2 Option C (self-maintained port) to Route E
(direct SDK adoption + thin product adapters); Option C kept as verified
fallback; spike-first with acceptance gates, no claim of final selection
- v2 report carried in verbatim as evidence base
Co-authored-by: multica-agent <github@multica.ai >
2026-10-25 22:06:31 +08:00
zonggong and multica-agent
575f2acfc5
HEL-847: apply v1.11 governance patch (GOV-006 mature-reuse principle, 60 items)
...
Audited manager handoff against af28ffd (v1.10):
- 59 original items byte-identical, open_items unchanged
- source hashes verified incl. other-agent-discussion sha256
- user quote 01a1734c verified against platform comment
- check_requirements passes vs main / hel-835-unified-review / product target
Co-authored-by: multica-agent <github@multica.ai >
2026-10-25 21:56:31 +08:00
zonggong and multica-agent
af28ffdcb5
HEL-835: evidence corrections per third review - 23 calls, day2 conclusion downgraded, old probe downgraded, null-fingerprint withdrawn, probe start deviation disclosed; 15/15 paired-window correction proof; real follow-up plan
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-25 09:17:34 +08:00
zonggong and multica-agent
c5167ca7c5
HEL-835: day2 handoff, dual-target requirement checks with handoff
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-25 09:06:59 +08:00
zonggong and multica-agent
65df25271e
HEL-835: guard v3 - done-delta streams settle ok on early close; 36/36
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-25 09:03:09 +08:00
zonggong and multica-agent
b98ab6ab50
HEL-835: deploy record updated for guard v2, restored service, prepared probe
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 14:53:01 +08:00
zonggong and multica-agent
96cdf07d73
HEL-835: probe seed backfills message_id provenance
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 14:52:15 +08:00
zonggong and multica-agent
468f0bbb6c
HEL-835: probe seed upsert memory_search flag
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 14:50:39 +08:00
zonggong and multica-agent
87afc34cd3
HEL-835: fix probe seed insert columns
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 14:50:26 +08:00
zonggong and multica-agent
e27274448d
HEL-835: fix probe seed companion identity_json shape
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 14:49:47 +08:00
zonggong and multica-agent
0b24fefc5d
HEL-835: synthetic retrieval probe seed script and runbook (approved plan, zero model calls)
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 14:49:06 +08:00
zonggong and multica-agent
9039311e29
HEL-835: guard v2 - unique call_id settlement, scene-bound categories, ledger validation, upstream close on cancel; 34/34 isolation proof
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 14:46:14 +08:00
zonggong and multica-agent
1fdca48153
HEL-835: guarded deploy record, audited call ledger, synthetic-retrieval plan (pending approval)
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 14:36:36 +08:00
zonggong and multica-agent
d7e5c00e80
HEL-835: deploy-layer durable call guard (caps 8 gist/6 turns/1 persona) + isolation proof 17/17 and assembly smoke
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 14:31:41 +08:00
zonggong and multica-agent
2ec9392aad
HEL-835: deploy record and rollback plan for isolated R3 instance on 8350
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 14:16:17 +08:00
zonggong and multica-agent
fc5e29469c
HEL-835: independent review evidence - rerun 225 pytest, web build/lint/42 vitest, 23/23 browser checks (chromium CDP), 30/30 e2e ControlledLLM isolated DB
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 13:58:13 +08:00
zonggong and multica-agent
2288471445
HEL-834: apply visual director memories page source package (6 modified + 9 new, verified against MANIFEST)
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 13:35:48 +08:00
白栖知 and multica-agent
89d53b6c53
HEL-833: restore runtime factory and verify R3 memory contracts
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 13:07:43 +08:00
白栖知 and multica-agent
78cab0456c
HEL-833: preserve R3 draft and regression stop evidence
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 12:55:58 +08:00
Chief Engineer and multica-agent
ee4459433c
HEL-832: R3 real-memory integration verification report, FTS probe evidence, handoff and follow-up construction cards (docs only)
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 12:46:53 +08:00
白栖知 and multica-agent
c285a0fd07
fix(r2): keep her self-narration and life within the approved room
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 12:03:08 +08:00
Chief Engineer and multica-agent
58d65aea05
HEL-828: wire life/persona/receipt confirmation onto 4575b275 (original author delivery, 12 files per MANIFEST in HEL-828-source-4575b275.zip)
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 11:08:53 +08:00
白栖知 and multica-agent
4575b27515
HEL-827: implement durable life, receipt-gated disclosure and persona layers
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 09:04:40 +08:00
Chief Engineer and multica-agent
2d97050c7e
HEL-825: review handoff (verified build/tests/browser checks/requirements; deploying 8320)
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 08:27:33 +08:00
Chief Engineer and multica-agent
e32a1ac0d2
HEL-825 review: link-card accessible-name selector fix (browser_check), evidence scripts, regenerated screenshots/recordings
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 08:27:06 +08:00
Chief Engineer and multica-agent
0bc4a9e68e
HEL-823 A3: days/memories, creation wizard, settings pages on cef8ae5 (author delivery, 15 modified + 1 handoff per CHANGES-HEL-823.json)
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 08:26:54 +08:00
白栖知 and multica-agent
cef8ae5581
HEL-824: land verified fixes on 4321aeb (small-screen first-press, real-time reading clock)
...
- 6 modified + handoff JSON per CHANGES-HEL-824.json, all hashes verified against git 4321aeb and package bytes
- rework_browser_check: skip full-text sheet at micro height (<420px design hides the control); migrate stale 返回日子 selector to 结束交谈 · 回到日子
- fresh run evidence: web build 25/25 unit tests, backend 142/142 (py3.12), all four browser checks PASS incl. new compact first-press and 700ms slow-frame sections (slow_frames_new_turn_to_reply_s=2.32s), layout regression 320/390/1024/1600 both themes
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 07:39:26 +08:00
白栖知 and multica-agent
4321aebfdc
HEL-822: fix handoff read_commit format
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 06:59:18 +08:00
白栖知 and multica-agent
e5fe01bfd1
HEL-822: review handoff JSON
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 06:59:07 +08:00
白栖知 and multica-agent
7db6677234
HEL-822: run all four browser checks; minimal mechanical check fixes + fresh run evidence
...
- browser_check.py: 视觉观察 → 视觉观察(模拟) (author renamed the aria-label, selector not migrated)
- import_check.py: handle the dirty-settings leave confirmation before opening the record (pre-existing gap, fails at base db571ba too)
- rework_browser_check.py: long-user-line reply budget 10s→60s (approved hel-799 dwell ≈2.4s/page), conditional 继续 resume (toLatest resumes flow in the approved prototype), 600ms settle before measuring compact typing nav transition
- regenerated docs/frontend + docs/rework evidence from this Linux run
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 06:58:20 +08:00
白栖知 and multica-agent
003d8c2cae
HEL-822: land HEL-821 A1+A2 source onto PR#4 base ( db571ba)
...
- 13 modified / 8 added / 1 deleted per CHANGES.json (author package 76bc120b)
- docs/requirements v1.10 + prototypes/hel-799 + PROVENANCE from bundle, verified byte-identical to 63799f0
- AGENTS.md + scripts/check_requirements.py restored from governance commit 63799f0
Co-authored-by: multica-agent <github@multica.ai >
2026-10-24 06:10:53 +08:00
白栖知 and multica-agent
db571ba204
HEL-783: repair readable dialogue, birth explanations and complete real page layouts
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-22 17:55:05 +08:00
白栖知 and multica-agent
f6614d4bf9
HEL-780: connect persistent companion and real streaming text chat
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-22 16:25:35 +08:00
白栖知 and multica-agent
6c3b09e693
HEL-748: implement S1 frontend with explicit local demo
...
Co-authored-by: multica-agent <github@multica.ai >
2026-10-22 00:56:18 +08:00
mobai
1e9b08aed8
docs: intro animation for 晚晚 (22s, pure canvas, zero assets)
...
Single-file HTML, Canvas 2D, no libraries, no images, no fonts to load.
The one idea worth explaining: the accent colour IS the valence.
moodColor(v) maps v in [-1,1] across cold blue -> neutral grey -> warm amber,
and every mark in the frame reads from it. So when she drops, the whole
picture goes cold -- no caption has to tell you she is sad. Same data,
three places: the trace colour, the memory hue, the retrieval highlight.
Timeline is a pure function render(t), no RAF accumulation. Every frame
renders in isolation, which means frames are reproducible, any resolution
can be re-exported, and the preview can be captured frame-by-frame instead
of screen-recorded.
Four acts:
0-6s membrane matter bounces off it, information passes through
6-12s heartbeat beats with no input; positive recovers fast, negative slow
12-17s memory points sink by salience; one gets pulled back up
by a mood-matching cue; floor at 0.03 so nothing vanishes
17-22s title
Also: ?t=12.5 freezes on that frame (for cover shots), and a REC button
uses canvas.captureStream + MediaRecorder to export webm directly.
Preview: 200 ANMF frames, 22000ms total, verified by parsing the RIFF/ANMF
chunks (Pillow does not expose per-frame WebP duration).
tools/render_preview.py renders frames via headless Chrome and assembles.
On this Windows box Python cannot spawn Chrome (0x80000003, same family as
the 0xC0000142 shell failure), so the render loop was driven from PowerShell
and the script only assembled. Both paths are documented in the script.
2026-10-19 20:33:13 +08:00
mobai
8dea68a25b
feat(think): four-tier model routing with budget guard
...
Corrects a common misconception: the 60s heartbeat must not call any LLM.
It runs the mood decay equation -- microseconds of float math. Giving it a
model is an architecture error, not a resource problem.
Real token spend lands in two places:
- per-turn input context (ontology + state + dyad + memory)
- background task frequency
So route by scene, not by time:
none rule/math tick, reach-out decision, fillers, avatar drive
low local small life events, memory gist, fact extract
standard mid + short speculative-response second segment
high flagship main dialogue, proactive message, crisis
Hard constraints:
- dialogue floor is LOW, never NONE (can get dumber, cannot lose lines)
- crisis never degrades (product constraint, not perf tuning)
- degradation is predictable: one rung per request, floor only at
the hard budget threshold
Cost levers, by actual payoff:
1. prompt caching (fixed prefix) -- by far the largest
2. upstream compression (small model condenses 20 memories to 3)
3. batching (one batch per 30min, not 20 single calls)
4. swapping to a smaller model -- smallest payoff, hurts persona
Also: cost degradation is narratable. 'Net error -> I zoned out' already
exists in the projection table, so being throttled is in-character and true.
- config.py: tiers / routing / budget, replacing llm+llm_fast+llm_background
- think/: scenes, budget, router, wiring
- models.yaml restructured around tiers
- SPEC gains 9.5
- 20 new tests; 78 total pass; ruff clean
2026-10-19 20:14:41 +08:00
mobai
1012d8bb79
chore: project foundation
...
Contracts (the shared language):
- percept / state / context / utterance / render / audio / capabilities
- Capability model instead of vendor schemas (see below)
Providers (capability-based abstraction):
- LLM + Embedding: OpenAI-compatible shape IS the standard, adopted directly
- ASR: internal contract is an event stream (partial -> final), because
/v1/audio/transcriptions has no partial and dialogue needs it for
endpointing. OpenAI adapter degrades to supports_partial=False.
- TTS: internal contract carries tags/emotion/style, because
/v1/audio/speech has no paralinguistics and [laughter]/[breath] are
the core of feeling alive. Unsupported providers are stripped AND
reported via Degradation -- silent degradation is forbidden.
- Avatar: no de-facto standard, custom RenderCmd protocol driven by State.
Core:
- mood: dynamical system, slow variables, negativity bias (grudge),
numbing after prolonged negativity
- bazi: four pillars -> numeric vector; 'ming' is data, not prose
- projection: phi, system event -> in-world statement; uncovered events
are counted as projection gaps
Storage:
- SQLite schema, three memory layers, dyad ledger
- accessibility floor 0.03 (not 0): forgettable but still there
Config split:
- models.yaml is the ONLY place model versions live
- character.yaml holds world rules / emotion params, no version numbers
58 tests pass; ruff clean.
2026-10-19 20:08:52 +08:00