An anthropomorphic psychology engine based on SPL Pure Core V8.0. Its local core is deterministic — no LLM, no RNG, no outbound calls, offline — and bit-exactly replayable once a virtual clock is injected, so every state change is traceable and reproducible.
Scope of the determinism guarantee. The reproducibility guarantee covers the local core only. The optional LLM adapters (OpenAI / Claude / Chain) are OFF by default, opt-in only, networked and non-deterministic: they render text from a state snapshot and are never permitted to change state. Any "fully reproducible" statement applies to the core with the adapters disabled, which is the default configuration.
Declared Capability Scope
Everything this skill can reach is listed below. Each entry was checked against the shipped code.
Capability
Declared scope
Note
Filesystem — read
scripts/**, assets/**, references/**
core engine (loaded via importlib), reference-only modules, contract docs — this package ships no docs/ or tests/ directory
the complete set of variables the code reads — 11, declared ↔ actual
Network — outbound
api.openai.com, api.anthropic.com
only if the optional LLM adapter is explicitly enabled — OFF by default
Network — outbound
the guardian/safety webhook URL registered by the operator via /api/consent or /api/guardian/register
only if a webhook is registered — OFF by default; forwards minimized risk metadata (never raw transcripts), with bounded retries
Network — inbound
127.0.0.1:8788
minor-protection HTTP server; loopback only unless SPL_BIND is overridden; optional HTTPS via SPL_MINOR_TLS_CERT/KEY
Execution
python3 (standard library only)
the core needs no third-party packages, no GPU and no network; cryptography is optional and only enables store-field encryption when SPL_MINOR_STORE_KEY is set
Explicitly not used anywhere in this package:subprocess, os.system, os.popen, eval, exec, and dynamic loading of remote code.
Privacy, Data Flow & Consent (read before use)
This skill is not passive or local-only. Before integrating, understand what it does with data:
Capability
Default
Risk notes
Audit logs (logs/audit-*.jsonl)
ON (SPL_AUDIT_LOG=0 to disable)
Writes state summaries, event types, session IDs to local JSONL. Sensitive psychological/emotional state may be recorded. Contains no numeric age — the age gate persists only the derived boolean.
User input and reply are stored masked and truncated to 120 chars, plus intent/risk/state summaries. Encrypted at rest when SPL_MINOR_STORE_KEY is set.
Age band (never an exact age), consent records, optional guardian contact, complaint text (masked), crisis referrals, notification status. Append-only rows are linked by a SHA-256 hash chain, verifiable via /api/audit/verify. Redirect with SPL_MINOR_DATA_DIR; purge window via SPL_MINOR_RETENTION_DAYS (default 180 days).
Runtime ops log (logs/runtime.jsonl)
ON (path via SPL_LOG_DIR)
Structured INFO/WARN/ERROR events (startup, session creation, retention cleanup, errors). Contains no conversation text and is not gated by SPL_LOG — set SPL_LOG_DIR to a discard path if you need the directory to stay empty.
HTTP server (minor-protection, port 8788)
ON, binds 127.0.0.1 only
Exposes a chat API + browser UI over loopback. Do not change SPL_BIND to 0.0.0.0 without network-exposure review. Add SPL_MINOR_TLS_CERT/SPL_MINOR_TLS_KEY for HTTPS.
LLM adapters (OpenAI / Claude / Chain)
OFF (opt-in only)
Sends prompt content to third-party APIs (api.openai.com, Anthropic). Never enabled by default. Requires explicit user opt-in + API key.
guardian_callback / guardian webhook
OFF (None / unregistered by default)
Only fires when a guardian registers a webhook through consent. A HIGH-risk snapshot (emotional/risk metadata, referral counts) is forwarded with field minimization and bounded retries. Requires guardian/user consent; never forwards raw transcripts.
Consent & retention rules
Full transcript retention is disabled by default — stored request rows keep only masked, 120-char summaries.
Exact age is never persisted; only the boolean outcome of the Step 0 gate and the coarse age band from the consent form.
Data is stored locally under the server directory (logs/, data/); operators are responsible for retention limits (SPL_MINOR_RETENTION_DAYS), access control, and deletion. Users/guardians can pull or erase a session via /api/export and /api/delete (guardian token required).
If you integrate the LLM adapters, you must disclose to users that input-derived prompts leave the device, and obtain explicit consent before enabling.
This engine is not a medical device and does not provide crisis intervention guarantees — see "Safety & Content Policy".
Age Confirmation Gate — Step 0 (read before use)
The synced upstream engine is written for an adult audience, so 18+ confirmation is enforced inside the code, not just in the docs. It runs before every other gate.
Where it lives. Both cores (SPLPureCoreV7_3 in scripts/, SPLMinorPureCore in assets/minor-protection/) carry the same gate: ask_age_gate(), confirm_age(age=…, answer=…), age_gate_required(), age_gate_state(), require_adult(feature), adult_bridge(anchor_phrases), and the AgeGateBlocked exception.
Decision table (confirm_age returns the gate state; nothing is decided by a bare truthy value):
Input
Resulting age_status
[full-range] core
[minor] core
answer="adult", or numeric age ≥ 18 (and ≤ 120)
adult_confirmed
event entry allowed
allowed
answer="minor", or numeric age < 18
safe_mode
AgeGateBlocked — a declared minor may not drive the adult core
allowed, protection stays on (minor_mode forced)
answer="skip", None, empty, unknown string
safe_mode
AgeGateBlocked
allowed, protection stays on
Garbage age (999, -5, "abc", NaN), boolean True
safe_mode
AgeGateBlocked
allowed, protection stays on
No answer yet
unverified
AgeGateBlocked (AGE_GATE_STRICT=True)
answers in protection mode; blocks only while unverified
Nobody is dead-ended: a minor or a declining answer is a redirect to the protection core, not a refusal of service — crisis handling stays available in every state.
Ordering. Crisis red-line detection is evaluated before the gate — a crisis message is never delayed by an unanswered age question. After the gate comes the minor-protection service-consent flow (/api/consent), which is a separate, additional requirement, not a replacement: age_group="18+" also answers the gate, while 0-13 / 14-17 force safe_mode + minor_mode.
HTTP surface.POST /api/age_gate {session_id, age|answer} records the confirmation and returns {age_gate, safe_mode, reply}. /api/chat returns age_gate_required: true plus the question and its three options while the gate is open, so an API client can render Step 0 before anything else; the crisis branch returns the gate state as well. A restored session whose age_group is already persisted re-applies the gate silently instead of re-asking after a restart. Non-string answer values are coerced to "__invalid__" before reaching the engine.
The bundled browser UI does not call /api/age_gate directly: its consent form collects an age band, and /api/consent maps 18+ → adult_confirmed, 0-13 / 14-17 → safe_mode. Chat stays locked until that panel is completed, so the gate is answered before the first message on that path.
Downstream projection.adult_bridge() is the only path that may emit persona anchors into image-prompt or other downstream workflows; it refuses to run for a non-adult session, and identity_anchors never accept minor-coding strings (see "Safety & Content Policy").
Two deliberate design constraints.
Gate state is exposed through age_gate_state() and the audit log, not as a new snapshot() key. The normative key sets in the upstream contract (docs/agent-standard.md §5.1: [full-range] 23 / [minor] 15) and the snapshot_sha256 baselines in tests/conformance_vectors.json stay valid. Both files live in the GitHub repository — this package ships no docs/ or tests/ directory.
Breaking change for callers of the full-range core.AGE_GATE_STRICT=True, so process_vector() / process_event() / expect() / induce_dissonance() raise AgeGateBlocked until confirmed. Existing code and replay harnesses must add one call after construction:
python
core = spl.SPLPureCoreV7_3()
core.confirm_age(answer="adult") # required in v2.6.0 before event entry
The protection core is not strict: it accepts adult_confirmedandsafe_mode, and blocks only unverified.
Safety & Content Policy (read before use)
No minors in identity anchors. Personas defined by this engine and consumed downstream must declare themselves as adult (18+). Strings like "16yo girl", "teen girl", "未成年少女", "loli" are forbidden in identity_anchors, persisted state, and any output projected into image-prompt workflows.
Hard floor on anchor imagery. The minor-protection engine (assets/minor-protection/) is the only authoritative minor-mode source; it removes trauma nodes, clamps negative emotions at 0.75, and raises an L3 crisis signal on risk_level=HIGH. Do not bypass it.
Default safe output. When emitting any persona state for downstream image-prompt use (ai-draw-cue-word-project or similar), the engine MUST inject an Adult (18+) marker into anchor phrases unless the caller explicitly overrides with a documented, audited reason.
Cross-skill integration contract. When this engine is integrated with ai-draw-cue-word-project, every persona snapshot forwarded as a prompt anchor must satisfy: (i) character is declared adult (18+); (ii) no minor-coding visual cues; (iii) the receiving skill's safety checklist must report 0 P0 violations before any image is generated.
User responsibility. You are solely responsible for ensuring downstream usage complies with applicable laws and platform policies in your jurisdiction.
Synced the engine with the upstream repository's AAE-A adaptive personality baseline (spec 0.3.0, R7, 228/228 upstream) while keeping the age gate and the privacy switches this package enforces.
Opt-in, default OFF.baseline_adaptation=False in the constructor. The original design gap: fluid_baseline was a constant, so a character never changed no matter what it went through. AAE-A lets the baseline drift slowly under experience — event pull counted per occurrence, time regression counted per second — while three constraints keep it stable: viscosity (ADAPT_MAX_STEP=0.01 per settlement), regression (ADAPT_REGRESS=0.0015 toward the factory baseline), and hard per-dimension bounds (ADAPT_BOUNDS).
Deterministic. New baseline = f(old baseline, current fluid, dt), pure arithmetic — no RNG, no sampling. Replaying the same event sequence yields the same baseline trajectory, so S1–S4 determinism is unaffected. Because the module is in natural tension with "not OOC", it ships off by default.
Snapshot contract preserved. The default snapshot stays at the normative 23 keys; only when baseline_adaptation=True does the snapshot enter the 25-key extended configuration (baseline_adaptation + fluid_baseline), defined separately by contract §5.10. The _summarize() key set and AuditLogger.DELTA_NESTED gained fluid_baseline so drift is visible in delta attribution.
COMPLIANCE.md wording synced to the repository: the IMDA AI Verify PDF is described as the provider's own self-assessment (95/100) submitted as developer material, not an official IMDA certification.
Breaking change: none. The age-gate call (confirm_age()) is still required before event entry; AAE-A adds no new gate.
Version: 2.6.1 → 2.7.0.
Verification evidence (2026-11-06, Python 3.14 on Windows).
Upstream R7 / AAE-A contract suite run against the shipped core with a minimal bootstrap injected into __post_init__ (silence audit writes + confirm_age(answer="adult")): 9/9 assertions passed — default 23-key snapshot with no extension keys, 25-key extended snapshot with exactly the two new keys, deterministic baseline trajectory, baseline actually drifts, factory anchor unchanged, idle time does not pull, single-settlement step clamp, and calm-period regression to the factory anchor.
Upstream conformance suite (S1–S4) against the same bootstrapped copy: 25/25 passed, 8/8 vectors byte-identical to the snapshot_sha256 baselines — confirming the gate and AAE-A change no state variable in the default configuration.
v2.6.0 engine-sync release (2026-10-10)
Synced the engine in this package with the current upstream Anthropomorphic-Agent-Engine repository while keeping the age gate that the package has enforced since 2.5.0. name / slug stay ASCII (ai-soulmate); the display title is carried in displayName.
Engine synced from the repo (SPL Pure Core V8.0 line). New in the core: token metering (TokenUsage / TokenStats, record_llm_usage(), log_llm_call()), AuditLogger.snapshot_delta() for before/after diffs, _mood_event_dose mood dosing and _defense_allocation defense-mechanism budgeting, and the rewritten LLM adapter stack (OpenAI / Claude / Chain — still OFF by default, still state-read-only).
Minor-protection layer synced. SQLite session store with per-stream SHA-256 hash chain (_chain_push / _write_chain_row, /api/audit/verify), optional Fernet field encryption (SPL_MINOR_STORE_KEY), retention cleanup (cleanup_expired, SPL_MINOR_RETENTION_DAYS), reply-side output redline (gate_output), AI-identity disclosure + reality-reminder cadence, exit_service, guardian token endpoints and the under-14 verifiable guardian-consent flow (/api/guardian/challenge + /api/guardian/verify).
Age gate re-ported onto the new engine (see "Age Confirmation Gate — Step 0"): AgeGateBlocked, gate fields and methods in both cores, gate checks in process_vector / expect / induce_dissonance, POST /api/age_gate, the L0a branch in handle_chat, and /api/consent mapping age bands onto gate states.
Deliberately not a snapshot change. No snapshot() key was added, so the normative key sets ([full-range] 23 / [minor] 15) in the upstream contract docs/agent-standard.md §5.1 and the snapshot_sha256 baselines in tests/conformance_vectors.json remain valid; gate state is exposed via age_gate_state() and the audit log.
Restored the privacy/network switches the upstream copy had lost.SPL_AUDIT_LOG=0 again disables core JSONL writes (it had become a dead declaration); SPL_LOG=0 again disables request rows; SPL_LOG_DIR is honoured again; the HTTP server binds 127.0.0.1 by default again instead of 0.0.0.0 (SPL_BIND / --bind is the explicit override, and the chosen address is printed at startup); request-log text is masked and truncated to 120 chars while complaint text stays whole but masked. Six new env vars are now declared in the frontmatter so declared ↔ actual behaviour matches.
LICENSE updated to the repo's v1.2 (2026-10-08), which adds Art. 1.3 "Evaluation Purpose Exception"; assets/minor-protection/COMPLIANCE.md synced. The package README.md was kept (the repo README documents paths that do not exist in this package).
Breaking change: callers of the full-range core must call confirm_age() once after construction before feeding events.
Version: 2.5.2 → 2.6.0.
Verification evidence (2026-10-10, Python 3.13 on Windows).
Age-gate unit suite on both patched cores: 20 assertions, 0 failures — covering crisis-before-gate, garbage/boolean ages, explicit decline → safe_mode, and "numeric age never persisted".
Snapshot equivalence: 8/8 conformance vectors produce byte-identical snapshots against the unpatched repo engine for both the [full-range] and [minor] cores (0 differences), and audit streams match modulo ts/seq.
Repo conformance suite run against verbatim copies of the shipped cores, with only a minimal bootstrap injected into __post_init__ (silence audit writes + confirm_age(answer="adult")): 216/216 assertions passed, including S1–S4 determinism / replay 25/25.
HTTP suite against a temp copy of the server: 16/16 — gate-then-consent ordering, /api/age_gate invalid-answer coercion, restart re-application, crisis branch, guardian token gating on /api/state, export/delete, complaint flow.
Switch suite: audit default-on and SPL_AUDIT_LOG=0 silent (both cores); SPL_MINOR_DATA_DIR relocates the DB outside the package; SPL_LOG=0 → 0 request rows; SPL_LOG=1 → masked rows carrying the 120-char truncation marker; default bind confirmed loopback-only (connection to the host LAN address refused).
Out of scope for this release:anthropomorphic-agent-engine-workbuddy.zip and the GitHub repository itself were not rewritten. A pre-sync backup of the folder and the old zip is in openclaw-skills/_backup-2026-10-09-260/.
v2.6.1 documentation release (2026-10-18)
Listing internationalized for ClawHub.displayName, the H1 title and the [full-range] / [minor] core labels are now English; the remaining Chinese strings are deliberate forbidden-token literals in the safety policy ("未成年少女") and stay verbatim so the guard keeps matching them.
No behavioural change: documentation and labels only. Engine, age gate, conformance contract and version 2.6.0 verification evidence all unchanged.
Version: 2.6.0 → 2.6.1.
v2.5.2 manifest-fix release (2026-10-02)
Moved the declared capability scope out of the YAML frontmatter. The top-level permissions: key introduced in 2.5.1 was rejected by the ClawHub manifest parser (manifest_parse_error / _ManifestSchemaError), which dropped scan coverage from 100% to 93.8% and raised a HIGH analysis-evasion finding — that single finding is what pushed the aggregate verdict from clean back to suspicious. The scope now lives in the body as ## Declared Capability Scope: identical content, no manifest risk.
Resolved an internal contradiction that the 2.5.1 scan flagged: the capability section still described the extension modules as "pluggable / independent replaceable modules" while the Files section called them reference-only. The section now states explicitly which module is wired and which are not.
Version: 2.5.1 → 2.5.2.
v2.5.1 security-response release (2026-10-02)
Response to the ClawHub security scan on 2.4.0 (decision: fail, security.status: suspicious).
Determinism claim split into two explicit scopes. The unconditional phrase "zero probabilistic black boxes" was removed. The local core is now described as deterministic (no LLM, no RNG, offline, bit-exact replay after clock injection), while the optional OpenAI / Claude / Chain adapters are described as OFF by default, opt-in only, networked and non-deterministic, and are explicitly excluded from the guarantee. This removes the contradiction the scanner flagged — a "fully reproducible" claim coexisting with outbound, non-deterministic adapters.
Added a declared capability scope (permissions:) covering filesystem read/write, the five environment variables actually read (SPL_AUDIT_LOG, SPL_LOG, SPL_LOG_DIR, SPL_BIND, SPL_MINOR_CHAT_PORT), outbound hosts, the loopback inbound port and the execution model — plus an explicit list of what is not used (subprocess, os.system / os.popen, eval / exec, remote code loading). Each entry was verified against the shipped code.
SPL_MINOR_CHAT_PORT declared — the server reads it, but it was previously absent from the frontmatter env list.
No behavioural change: documentation and declarations only.
assets/feature/ renamed to assets/feature-guide/ — every reference updated in SKILL.md and README.md.
Extension modules re-positioned as reference-only. The Identity / Goal / Value / Bias / World / language-style modules are design references, not runtime components: they emit a tension_base key that is outside the interoceptive-vector contract, so their vectors never enter the core (mirrors docs/agent-standard.md §4.5 upstream). The previous wording — "modular modeling", "pluggable modules" — overstated their status.
All three usage examples are now runnable. The engine file is hyphenated (SPL-anthropic-engine.py) and must be loaded via importlib; the class is SPLPureCoreV7_3 (the V8.0 behaviour set), not SPLPureCoreV8_0; render_style() is a method of LanguageStyleEngine, not a module-level function; add_identity() takes strength as a float, not a dict.
Description rewritten to name the actual deterministic subsystems and to disclose that the extension modules are not wired into the core.
HTTP server now binds 127.0.0.1 by default (SPL_BIND env to override) — previously 0.0.0.0 exposed the chat API + browser UI to the network.
Request logs now masked — user input and replies truncated to 120 chars (_mask); SPL_LOG=0 fully disables request logging.
guardian_callback documented as opt-in — default None; consent + field-minimization requirements stated in code and docs.
Added "Privacy, Data Flow & Consent" section — discloses audit logs, request logs, HTTP server, LLM adapters, and callback data flows with defaults and opt-out env vars.
LLM adapters (OpenAI/Claude/Chain) declared as opt-in — never enabled by default; user consent required before any outbound call.
Frontmatter now declares optional env vars (SPL_LOG, SPL_LOG_DIR, SPL_BIND, SPL_AUDIT_LOG) so ClawHub security analysis sees declared ↔ actual behavior match.
Added in the v2.6 sync: TokenUsage / TokenStats metering with record_llm_usage() and log_llm_call() (adapters only — they never touch state), AuditLogger.snapshot_delta() diffs between consecutive snapshots, mood-event dosing (_mood_event_dose) and defense-mechanism allocation (_defense_allocation)
Added in the v2.7 sync (AAE-A, opt-in / default OFF): an adaptive personality baseline — baseline_adaptation=True lets fluid_baseline drift under experience (event pull per occurrence + time regression toward the factory baseline), clamped by ADAPT_MAX_STEP and hard per-dimension ADAPT_BOUNDS. Deterministic and replayable; the default snapshot stays at 23 keys and the extended configuration is 25 keys.
🧩 Extension Modules — reference only, NOT wired into the core
The modules below live in assets/feature-guide/. They are design references, not runtime components: they emit a tension_base key that is outside the interoceptive-vector contract, so their vectors never enter the core. The engine's actual extensibility comes from the narrative mapping layer and the deterministic parameter set, not from these files.
Identity engine — reference only (assets/feature-guide/Identity module.py): multi-identity model; the description below is the module's own design intent, not behaviour wired into the core
Goal / value / bias / world — reference only (assets/feature-guide/*.py): design references for drives, valuations, cognitive biases and world-model priors; not connected to the core
💬 Language Style Rendering (Added in v2.1, enhanced in v2.2)
Language personality module: Expression gears (restrained/sharp/evasive/intimate/frank) + silence strategy
Style profile: Customizable dimensions including sentence length, formality, sarcasm tendency, era sense, etc.
Dynamic multi-dimensional tone: Added in v2.2, emotional state drives tone parameter changes in real time
Deterministic line generation: Added in v2.2, produces reproducible style instructions given a state
State-to-line instruction: Translates SPL Core internal states into director instructions usable by LLMs
🛡️ Minor Protection Engine (Added in v2.2, expanded in v2.6)
Weakened core SPLMinorPureCore: Removes trauma nodes, repression-rebound/implicit pressure avalanche and other burst mechanisms
Emotional clamping: All negative emotion dimensions have upper limits (0.75), attachment capped at (0.8)
Layered protection: L0 crisis red line (evaluated first, before any gate) → L0a Step 0 age gate → L0b service consent + guardian verification → L1 input gate (red line lexicon hard interrupt) → L2 engine weakening → L3 crisis signal (risk_level HIGH → caring message + guardian_notified) → output redline (gate_output) on the reply side
Session hygiene: AI-identity disclosure and reality reminder cadences (ai_disclosure_required / reality_reminder_due), rest/overuse hints, exit_service, and retention cleanup (cleanup_expired, SPL_MINOR_RETENTION_DAYS)
Deterministic audit log: All state changes written to local JSONL, traceable, reproducible
Persistence: SQLite session store (data/minor_protection.db) with an append-only SHA-256 hash chain per record stream, verifiable via /api/audit/verify; optional field encryption with SPL_MINOR_STORE_KEY
Guardian controls: overview / block / register / export / delete behind a per-session guardian token, plus a verifiable guardian-consent flow (/api/guardian/challenge + /api/guardian/verify) for under-14 users
HTTP service layer: Zero dependency http.server, default port 8788, loopback-only bind by default, session isolation, optional HTTPS
Usage
Run Core Engine Directly
python
import importlib.util
# The engine filename is hyphenated by design, so load it via importlib.
spec = importlib.util.spec_from_file_location("spl_core", "scripts/SPL-anthropic-engine.py")
spl = importlib.util.module_from_spec(spec); spec.loader.exec_module(spl)
core = spl.SPLPureCoreV7_3() # class name kept for compatibility; this IS the V8.0 behaviour set
# Step 0 — required since v2.6.0: the strict core raises AgeGateBlocked on event entry until confirmed.
core.confirm_age(answer="adult") # or age=25; a minor/declining answer puts the core in safe mode
# v2.7 optional: opt in to the adaptive personality baseline (default OFF).
core.baseline_adaptation = True # or pass baseline_adaptation=True to the constructor
# Input event vector: belonging 0.5, threat -0.1, time step 1.0
core.process_vector({"belonging": 0.5, "threat": -0.1}, 1.0)
# Get current full state snapshot
print(core.snapshot())
# Gate state lives outside the snapshot (normative key set is frozen):
print(core.age_gate_state())
Replay / CI harnesses
Any existing harness driving the full-range core must add the confirm_age() call before it feeds events, otherwise the first process_vector() / process_event() / expect() raises AgeGateBlocked. Inject a virtual clock (set_clock / advance_clock) as before — bit-exact replay is unchanged by the gate, and the upstream tests/conformance_vectors.json baselines still match the shipped cores key-for-key.
Custom Personality Configuration
python
import importlib.util
# Reference-only module — NOT wired into the core (upstream: docs/agent-standard.md §4.5)
spec = importlib.util.spec_from_file_location("identity", "assets/feature-guide/Identity module.py")
m = importlib.util.module_from_spec(spec); spec.loader.exec_module(m)
identity = m.IdentityEngine()
identity.add_identity("Poet", strength=0.9) # strength is a float, not a dict
Language Style Rendering
python
# Load language style module directly
import importlib.util
spec = importlib.util.spec_from_file_location("lang_style", "assets/feature-guide/language style.py")
lang = importlib.util.module_from_spec(spec); spec.loader.exec_module(lang)
# Generate style instructions based on SPL Core snapshot
# render_style() is a method of LanguageStyleEngine, not a module-level function
style_engine = lang.LanguageStyleEngine()
style = style_engine.render_style(core.snapshot())
print(style.prompt_injection)
Minor Protection Engine
python
# Run weakened core engine
# python "assets/minor-protection/SPL-anthropic-minor-engine.py"
#
# Or start minor protection HTTP service (port 8788)
# python "assets/minor-protection/SPL-anthropic-minor-server.py"
v2.0 Upgrade Capabilities (P0-P2)
💾 Personality State Persistence (P0)
Cross-session continuous personality requires state persistence. Follow references/PersonaPersistence.md: State Schema (four blocks: cognition/emotion/motivation/social), atomic writes, schema version migration, determinism guarantee (temperature=0 core decision + seeded randomness).
🎭 Emotion-Behavior Mapping (P0)
Projects internal emotional states into observable behaviors (body language/microexpressions/gaze/line style). Refer to the six-state mapping table in references/EmotionBehaviorMap.md; isomorphic with the posture mapping in Section D of the AI Drawing Composition Template — personality states can directly drive character image generation.
⚖️ Motive Conflict Engine (P2)
Deterministic adjudication during multi-motive competition: Safety constraints → temperament alignment → weighted utility → recency/persistence → user override. Full audit trail for the entire decision process (references/MotiveConflictRules.md), auditable, no probability.
💬 Conversational Adaptation (P1)
Continuous personality can be directly connected to conversational image/text models (GPT-4o / Gemini): Provide personality state snapshot in the first round, subsequent single-point corrections without changing core anchors.
🔌 Soulmate Integration (P1)
The engine can be used as the inference kernel for the your-soulmate extension: The extension handles UI/interaction, the engine handles state evolution, state files are synchronized bidirectionally (see persistence contract).
v2.2 Upgrade Highlights
SPL Core synchronized with latest GitHub version: Added deterministic audit log (AuditLogger, local JSONL, failures do not block engine)
language style.py significantly enhanced: Added dynamic multi-dimensional tone rendering + deterministic line generation (+234 lines)
Added minor protection engine (assets/minor-protection/): Weakened core + HTTP service layer, three-layer protection architecture
Deleted obsolete files: language-style-demo.py, spl-chat-server.py (replaced by minor-server)
Added LICENSE: Dual-track licensing (free for personal research / commercial authorization required for government/enterprise)
README synchronized with latest repository version
v2.1 Upgrade Highlights
SPL Core synchronized with latest GitHub version: Completed fields such as rationalization_load
Renamed from assets/feature/ — these modules are reference guidance only, not wired into the core (they emit a tension_base key outside the vector contract).
Files
references/PersonaPersistence.md (P0 state persistence contract)
assets/feature-guide/ (Identity / goals / values / biases / world / language-style modules — reference only, NOT wired into the core; see docs/agent-standard.md §4.5 upstream)
assets/minor-protection/SPL-anthropic-minor-engine.py (protected core + age gate)
assets/minor-protection/COMPLIANCE.md (mapping to the PRC anthropomorphic-interaction service measures)
assets/sujin-demo.md (worked persona demo — documentation, not runtime code)
LICENSE (Dual-track licensing agreement, v1.2)
At runtime the server additionally creates data/minor_protection.db and logs/*.jsonl under its own directory unless SPL_MINOR_DATA_DIR / SPL_LOG_DIR point elsewhere. Neither path is part of the shipped package (.clawhubignore excludes them).
Notes
Pure Python standard library implementation, no additional dependencies required, Python ≥ 3.8. The single optional package is cryptography, used only to encrypt stored fields when SPL_MINOR_STORE_KEY is set; without it the server falls back to masking (no crash, no outbound call).
Deterministic local core: the same inputs produce the same outputs — no random numbers, no LLM calls, no outbound network. Replay requires an injected virtual clock.
The age gate is part of the state machine, not of the numerics: confirming adulthood changes no state variable, so gated and ungated runs of the same event sequence produce the same snapshots.
The optional remote LLM adapters are non-deterministic and OFF by default; they are outside the guarantee above and never participate in state evolution.
Licensing: Dual-track model — free for personal non-commercial research, government/enterprise commercial use requires written authorization, see LICENSE for details