Add Persona culture stack golf harness
This commit is contained in:
Meta Vens
parent
aeb9fa4c5f
commit
e441cf33f4
17 changed files with 1830 additions and 13 deletions
1
.gitignore
vendored
1
.gitignore
vendored
|
|
@ -9,6 +9,7 @@ state/scratch-compaction-*.md
|
|||
state/scratch-runtime/
|
||||
.weksa-runs/
|
||||
.weksa-smoke/
|
||||
examples/persona-lowering/*/runs/
|
||||
node_modules/
|
||||
dist/
|
||||
build/
|
||||
|
|
|
|||
17
data/cultural-ontology/README.md
Normal file
17
data/cultural-ontology/README.md
Normal file
|
|
@ -0,0 +1,17 @@
|
|||
# Cultural Ontology Store
|
||||
|
||||
This directory holds draft Weksa cultural and subcultural ontology profiles used
|
||||
for ontological lowering, syntax, grammar, discourse, and surface-affordance
|
||||
selection.
|
||||
|
||||
Live pipeline shape:
|
||||
|
||||
1. Weksa stores reusable cultures/subcultures here and in semantic retrieval
|
||||
storage such as Qdrant.
|
||||
2. A Persona state references the relevant culture stack.
|
||||
3. The Persona produces interlingua intent from current state and situation.
|
||||
4. Weksa lowers that interlingua through the referenced culture stack.
|
||||
|
||||
Persona state owns current intent, memory pressure, and relationship stance.
|
||||
Cultural ontology owns reusable salience, affordances, and constraints. Qdrant
|
||||
may retrieve candidates, but accepted ontology remains typed state.
|
||||
28
data/cultural-ontology/catalog.yaml
Normal file
28
data/cultural-ontology/catalog.yaml
Normal file
|
|
@ -0,0 +1,28 @@
|
|||
schema_version: weksa.cultural_ontology_catalog.v0
|
||||
catalog_id: weksa.cultural_ontology.catalog.v0
|
||||
status: draft
|
||||
qdrant:
|
||||
intended_collection: weksa_cultural_ontology_profiles
|
||||
payload_keys:
|
||||
- profile_id
|
||||
- kind
|
||||
- language_codes
|
||||
- regions
|
||||
- evidence_refs
|
||||
- status
|
||||
ownership_note: >
|
||||
Qdrant owns retrieval over culture/subculture chunks. It does not own
|
||||
accepted ontology, activation, or lowering authority.
|
||||
profiles:
|
||||
- profile_id: weksa.culture.dutch_american_diaspora.v0
|
||||
path: data/cultural-ontology/cultures/dutch-american-diaspora.yaml
|
||||
- profile_id: weksa.culture.western_europe_maritime_childhood.v0
|
||||
path: data/cultural-ontology/cultures/western-europe-maritime-childhood.yaml
|
||||
- profile_id: weksa.culture.portugal_resident_algarve_lisbon.v0
|
||||
path: data/cultural-ontology/cultures/portugal-resident-algarve-lisbon.yaml
|
||||
- profile_id: weksa.culture.texas_houston_us_adolescence.v0
|
||||
path: data/cultural-ontology/cultures/texas-houston-us-adolescence.yaml
|
||||
- profile_id: weksa.subculture.online_game_dev_discord_pre2025.v0
|
||||
path: data/cultural-ontology/subcultures/online-game-dev-discord-pre2025.yaml
|
||||
- profile_id: weksa.subculture.gamecult_open_source_crypto_anarchist.v0
|
||||
path: data/cultural-ontology/subcultures/gamecult-open-source-crypto-anarchist.yaml
|
||||
58
data/cultural-ontology/cultures/dutch-american-diaspora.yaml
Normal file
58
data/cultural-ontology/cultures/dutch-american-diaspora.yaml
Normal file
|
|
@ -0,0 +1,58 @@
|
|||
schema_version: weksa.cultural_ontology_profile.v0
|
||||
profile_id: weksa.culture.dutch_american_diaspora.v0
|
||||
kind: diaspora_identity
|
||||
status: draft_guarded
|
||||
language:
|
||||
codes:
|
||||
- en
|
||||
- nl
|
||||
community:
|
||||
regions:
|
||||
- Netherlands
|
||||
- United States
|
||||
speech_community: >
|
||||
People whose self-description or life history crosses Dutch origin and
|
||||
American nationality/residence. This profile is not a dialect claim.
|
||||
activation:
|
||||
allowed_when:
|
||||
- persona_state_references_profile
|
||||
- interlingua_mentions_origin_nationality_or_cross_cultural_identity
|
||||
forbidden_when:
|
||||
- used_to_infer_accent_or_fluency_without_evidence
|
||||
- used_as_generic_dutch_or_generic_american_stereotype
|
||||
salience_axes:
|
||||
plural_national_identity:
|
||||
axis_id: plural_national_identity
|
||||
domain: identity_indexing
|
||||
description: Birthplace, citizenship, residence, and cultural identification may diverge.
|
||||
relevant_distinctions:
|
||||
- distinction_id: birthplace_vs_citizenship
|
||||
label: Birthplace versus citizenship
|
||||
meaning: Being born in one country and holding identity/citizenship in another are separate ontology fields.
|
||||
lowering_questions:
|
||||
- Does the utterance need origin, nationality, residence, or cultural affiliation?
|
||||
required_when:
|
||||
- source_mentions_identity_origin_or_nationality
|
||||
forbidden_when:
|
||||
- scene_only_requires_casual_banter
|
||||
evidence_refs:
|
||||
- discord:805822798185627718
|
||||
- discord:1030577958215225396
|
||||
evidence_ledger:
|
||||
- ref: discord:805822798185627718
|
||||
quote: "I live in Portugal at the moment, though I am a Netherlands-born US citizen - lived mostly in Texas"
|
||||
- ref: discord:1030577958215225396
|
||||
quote: "Dual nationality, Dutch American"
|
||||
- ref: discord:862490040755683348
|
||||
quote: "I was born in the Netherlands but I'm a US citizen and did high school in Houston, Texas."
|
||||
linguistic_affordances:
|
||||
grammar_features: []
|
||||
phonology_features: []
|
||||
lexicon_features: []
|
||||
discourse_patterns: []
|
||||
orthography_features: []
|
||||
code_switching:
|
||||
allowed: false
|
||||
constraints:
|
||||
- Do not infer Dutch code switching from diaspora identity alone.
|
||||
patterns: []
|
||||
|
|
@ -0,0 +1,84 @@
|
|||
schema_version: weksa.cultural_ontology_profile.v0
|
||||
profile_id: weksa.culture.portugal_resident_algarve_lisbon.v0
|
||||
kind: regional_residence
|
||||
status: draft_guarded
|
||||
language:
|
||||
codes:
|
||||
- en
|
||||
- pt
|
||||
community:
|
||||
regions:
|
||||
- Portugal
|
||||
- Algarve
|
||||
- Lisbon
|
||||
- Tavira
|
||||
speech_community: >
|
||||
Portugal as lived residence and locality rather than tourist backdrop.
|
||||
activation:
|
||||
allowed_when:
|
||||
- persona_state_references_profile
|
||||
- interlingua_mentions_portugal_residence_locality_bureaucracy_or_timing
|
||||
forbidden_when:
|
||||
- used_for_broad_portuguese_culture_without_locale_review
|
||||
salience_axes:
|
||||
lived_portugal:
|
||||
axis_id: lived_portugal
|
||||
domain: identity_indexing
|
||||
description: Portugal references can be local/home references, including Algarve/Lisbon/Tavira specificity.
|
||||
relevant_distinctions:
|
||||
- distinction_id: current_or_returned_residence
|
||||
label: Current or returned residence
|
||||
meaning: Portugal can be present-tense home context, not childhood-only memory.
|
||||
lowering_questions:
|
||||
- Is Portugal being invoked as current location, childhood location, or comparison frame?
|
||||
required_when:
|
||||
- source_mentions_portugal_or_portuguese_residence
|
||||
forbidden_when:
|
||||
- scene_has_no_place_salience
|
||||
evidence_refs:
|
||||
- discord:581220303414231117
|
||||
- discord:834858944013926421
|
||||
- discord:888820124344254504
|
||||
evidence_ledger:
|
||||
- ref: discord:581220303414231117
|
||||
quote: "I'm in the Algarve now"
|
||||
- ref: discord:834858944013926421
|
||||
quote: "I live in Portugal now"
|
||||
- ref: discord:888820124344254504
|
||||
quote: "But I'm currently in Lisbon"
|
||||
- ref: discord:1023774733789040640
|
||||
quote: "if you wanna move to Portugal you're gonna have to get used to not getting things on time"
|
||||
linguistic_affordances:
|
||||
grammar_features: []
|
||||
phonology_features: []
|
||||
lexicon_features: []
|
||||
discourse_patterns:
|
||||
- pattern_id: portugal_timing_joke_guarded
|
||||
label: Portugal timing joke, guarded
|
||||
status: draft
|
||||
domain:
|
||||
layer: discourse
|
||||
category: humor
|
||||
subcategory: local_bureaucracy_timing
|
||||
interactional_function: locally_grounded_timing_joke
|
||||
sequence_shape:
|
||||
- playful_warning
|
||||
- local_timing_generalization
|
||||
adjacency_constraints:
|
||||
- addressee_is_discussing_moving_or_living_in_portugal
|
||||
activation:
|
||||
allowed_when:
|
||||
- local_portugal_residence_context
|
||||
- joking_register
|
||||
forbidden_when:
|
||||
- formal_cultural_description
|
||||
evidence:
|
||||
source_refs:
|
||||
- discord:1023774733789040640
|
||||
confidence: low
|
||||
orthography_features: []
|
||||
code_switching:
|
||||
allowed: false
|
||||
constraints:
|
||||
- This profile alone does not authorize Portuguese code switching.
|
||||
patterns: []
|
||||
|
|
@ -0,0 +1,56 @@
|
|||
schema_version: weksa.cultural_ontology_profile.v0
|
||||
profile_id: weksa.culture.texas_houston_us_adolescence.v0
|
||||
kind: adolescence_residence
|
||||
status: draft_guarded
|
||||
language:
|
||||
codes:
|
||||
- en
|
||||
community:
|
||||
regions:
|
||||
- United States
|
||||
- Texas
|
||||
- Houston
|
||||
speech_community: >
|
||||
US/Texas adolescent institutional context, especially Houston high school
|
||||
and later critique of American debt/institutional pathways.
|
||||
activation:
|
||||
allowed_when:
|
||||
- persona_state_references_profile
|
||||
- interlingua_mentions_us_texas_school_debt_or_american_institutions
|
||||
forbidden_when:
|
||||
- used_to_force_texan_dialect_markers
|
||||
salience_axes:
|
||||
american_institutional_distance:
|
||||
axis_id: american_institutional_distance
|
||||
domain: stance
|
||||
description: US institutions can be lived experience and object of critique rather than foreign abstraction.
|
||||
relevant_distinctions:
|
||||
- distinction_id: debt_train_refusal
|
||||
label: American debt train refusal
|
||||
meaning: Avoiding US education/debt pathways can be a first-person institutional stance.
|
||||
lowering_questions:
|
||||
- Is the utterance about education, debt, leaving the US, or institutional pressure?
|
||||
required_when:
|
||||
- source_mentions_us_debt_or_school_path
|
||||
forbidden_when:
|
||||
- casual_fixture_without_institutional_topic
|
||||
evidence_refs:
|
||||
- discord:1160260490690306148
|
||||
evidence_ledger:
|
||||
- ref: discord:805822798185627718
|
||||
quote: "lived mostly in Texas"
|
||||
- ref: discord:862490040755683348
|
||||
quote: "did high school in Houston, Texas"
|
||||
- ref: discord:1160260490690306148
|
||||
quote: "I specifically left the US after high school so as not to climb onto the traditional American debt train"
|
||||
linguistic_affordances:
|
||||
grammar_features: []
|
||||
phonology_features: []
|
||||
lexicon_features: []
|
||||
discourse_patterns: []
|
||||
orthography_features: []
|
||||
code_switching:
|
||||
allowed: false
|
||||
constraints:
|
||||
- Do not infer Southern or Texan dialect surface markers from residence alone.
|
||||
patterns: []
|
||||
|
|
@ -0,0 +1,53 @@
|
|||
schema_version: weksa.cultural_ontology_profile.v0
|
||||
profile_id: weksa.culture.western_europe_maritime_childhood.v0
|
||||
kind: mobility_childhood
|
||||
status: draft_guarded
|
||||
community:
|
||||
regions:
|
||||
- France
|
||||
- Spain
|
||||
- Portugal
|
||||
- coastal_western_europe
|
||||
speech_community: >
|
||||
Mobile childhood organized around sailing, ports, and cross-border Western
|
||||
European movement. This profile is owner-attested for the Metame fixture and
|
||||
needs more Discord corroboration before broader use.
|
||||
activation:
|
||||
allowed_when:
|
||||
- persona_state_references_profile
|
||||
- interlingua_mentions_childhood_origin_mobility_boats_or_home
|
||||
forbidden_when:
|
||||
- used_as_decorative_nautical_metaphor_without_context
|
||||
salience_axes:
|
||||
mobile_home:
|
||||
axis_id: mobile_home
|
||||
domain: identity_indexing
|
||||
description: Home can be vessel, coast, port, family movement, and country sequence rather than one fixed town.
|
||||
relevant_distinctions:
|
||||
- distinction_id: vessel_as_childhood_home
|
||||
label: Vessel as childhood home
|
||||
meaning: A sailboat childhood makes movement and locality primary ontology fields.
|
||||
lowering_questions:
|
||||
- Does the line invoke home, travel, borders, coast, or rootedness?
|
||||
required_when:
|
||||
- source_mentions_childhood_or_home
|
||||
forbidden_when:
|
||||
- scene_has_no_mobility_or_home_salience
|
||||
evidence_refs:
|
||||
- owner:2026-06-10:sailboat_france_spain_portugal_until_6
|
||||
evidence_ledger:
|
||||
- ref: owner:2026-06-10:sailboat_france_spain_portugal_until_6
|
||||
quote: "I was born in the Netherlands, grew up on a sailboat traveling France, Spain, staying in Portugal until I was 6, moved to the US."
|
||||
- ref: discord-search-gap:sailboat_childhood
|
||||
summary: First semantic search did not locate a direct Discord message for this exact childhood account.
|
||||
linguistic_affordances:
|
||||
grammar_features: []
|
||||
phonology_features: []
|
||||
lexicon_features: []
|
||||
discourse_patterns: []
|
||||
orthography_features: []
|
||||
code_switching:
|
||||
allowed: false
|
||||
constraints:
|
||||
- Do not infer French, Spanish, Portuguese, or Dutch fluency from movement alone.
|
||||
patterns: []
|
||||
|
|
@ -0,0 +1,51 @@
|
|||
schema_version: weksa.cultural_ontology_profile.v0
|
||||
profile_id: weksa.subculture.gamecult_open_source_crypto_anarchist.v0
|
||||
kind: political_technical_community
|
||||
status: draft_guarded
|
||||
language:
|
||||
codes:
|
||||
- en
|
||||
community:
|
||||
regions:
|
||||
- online
|
||||
speech_community: >
|
||||
GameCult-adjacent open-source, crypto-anarchist, game-development, and
|
||||
engineering practice where ownership, inspectability, debt, authority, and
|
||||
tool coherence are culturally salient.
|
||||
activation:
|
||||
allowed_when:
|
||||
- persona_state_references_profile
|
||||
- interlingua_mentions_tools_authority_open_source_debt_game_dev_or_engineering
|
||||
forbidden_when:
|
||||
- used_to_turn_random_banter_into_manifesto
|
||||
salience_axes:
|
||||
authority_and_tool_coherence:
|
||||
axis_id: authority_and_tool_coherence
|
||||
domain: stance
|
||||
description: Systems are judged by ownership, inspectability, agency, and whether they actually work.
|
||||
relevant_distinctions:
|
||||
- distinction_id: open_source_anti_custody
|
||||
label: Open source anti-custody
|
||||
meaning: Open access and inspectability are political and practical values.
|
||||
lowering_questions:
|
||||
- Is the line judging a tool, institution, ownership structure, or coordination method?
|
||||
- Should the interlingua preserve anti-custody or open-access salience?
|
||||
required_when:
|
||||
- source_mentions_open_source_or_institutional_authority
|
||||
forbidden_when:
|
||||
- casual_social_move_only
|
||||
evidence_refs:
|
||||
- discord:862490040755683348
|
||||
linguistic_affordances:
|
||||
grammar_features: []
|
||||
phonology_features: []
|
||||
lexicon_features: []
|
||||
discourse_patterns: []
|
||||
orthography_features: []
|
||||
code_switching:
|
||||
allowed: false
|
||||
constraints: []
|
||||
patterns: []
|
||||
evidence_ledger:
|
||||
- ref: discord:862490040755683348
|
||||
quote: "I got my bachelor degree in game development last year. I'm a crypto-anarchist open source activist"
|
||||
|
|
@ -0,0 +1,288 @@
|
|||
schema_version: weksa.cultural_ontology_profile.v0
|
||||
profile_id: weksa.subculture.online_game_dev_discord_pre2025.v0
|
||||
kind: community_of_practice
|
||||
status: draft_guarded
|
||||
language:
|
||||
codes:
|
||||
- en
|
||||
community:
|
||||
regions:
|
||||
- online_discord
|
||||
speech_community: >
|
||||
Pre-2025 GameCult/Aquarium-ish Discord collaboration where game design,
|
||||
sound, engineering, jokes, and casual status play cohabit the same rooms.
|
||||
activation:
|
||||
allowed_when:
|
||||
- persona_state_references_profile
|
||||
- target_medium_is_discord
|
||||
- target_period_is_pre_2025_or_history_fixture
|
||||
forbidden_when:
|
||||
- formal_current_project_doctrine_is_target
|
||||
salience_axes:
|
||||
casual_room_temperature:
|
||||
axis_id: casual_room_temperature
|
||||
domain: discourse_patterns
|
||||
description: Compact, socially alive wording that assumes shared room context.
|
||||
relevant_distinctions:
|
||||
- distinction_id: banter_over_explanation
|
||||
label: Banter over explanation
|
||||
meaning: The line may be short, fragmentary, and joke-shaped when context supplies the frame.
|
||||
lowering_questions:
|
||||
- Can the utterance be one sentence or fragment?
|
||||
- Does explanation weaken the social move?
|
||||
required_when:
|
||||
- fixture_style_tags_include_casual
|
||||
forbidden_when:
|
||||
- formal_review_or_doctrine_is_requested
|
||||
evidence_refs:
|
||||
- discord:802911591288537118
|
||||
- discord:820077384572338176
|
||||
linguistic_affordances:
|
||||
grammar_features:
|
||||
- feature_id: fragmentary_like_comparison
|
||||
label: Fragmentary Like comparison
|
||||
status: draft
|
||||
domain:
|
||||
layer: grammar
|
||||
category: comparison
|
||||
subcategory: fragment
|
||||
description: >
|
||||
A joke-description may start with "Like..." and remain fragmentary when
|
||||
it is an immediate continuation of collaborative design talk.
|
||||
realization:
|
||||
function: casual_comic_comparison
|
||||
surface_strategy: "Like a really terrible <thing> that <absurd property>"
|
||||
examples:
|
||||
- "Like a really terrible engine that sounds like coconuts when you use it"
|
||||
activation:
|
||||
allowed_when:
|
||||
- collaborative_design_banter
|
||||
forbidden_when:
|
||||
- standalone_formal_explanation
|
||||
requires_profile_authority: true
|
||||
minimum_density: light
|
||||
maximum_density: normal
|
||||
evidence:
|
||||
source_refs:
|
||||
- discord:802911591288537118
|
||||
confidence: medium
|
||||
phonology_features: []
|
||||
lexicon_features:
|
||||
- feature_id: casual_recoil_oof
|
||||
label: Casual recoil marker oof
|
||||
status: draft
|
||||
domain:
|
||||
layer: lexicon
|
||||
category: stance_marker
|
||||
subcategory: embarrassment
|
||||
lexical_items:
|
||||
- form: oof
|
||||
gloss: amused impact or discomfort
|
||||
sense: playful_recoil
|
||||
register: casual_discord
|
||||
allowed_speaker_standing: speaker_can_self_deprecate
|
||||
forbidden_senses: []
|
||||
collocations:
|
||||
- "oof, don't tell me"
|
||||
activation:
|
||||
allowed_when:
|
||||
- compliment_or_trait_read_lands
|
||||
forbidden_when:
|
||||
- serious_apology_or_harm_context
|
||||
requires_profile_authority: true
|
||||
minimum_density: light
|
||||
maximum_density: light
|
||||
evidence:
|
||||
source_refs:
|
||||
- discord:1037314100931338260
|
||||
confidence: high
|
||||
- feature_id: mock_challenge_coward
|
||||
label: Mock challenge coward
|
||||
status: draft
|
||||
domain:
|
||||
layer: lexicon
|
||||
category: stance_marker
|
||||
subcategory: friendly_roast
|
||||
lexical_items:
|
||||
- form: coward
|
||||
gloss: mock insult
|
||||
sense: friendly_status_challenge
|
||||
register: casual_discord
|
||||
allowed_speaker_standing: active_banter_with_known_participant
|
||||
forbidden_senses:
|
||||
- actual_contempt
|
||||
collocations:
|
||||
- "then you coward"
|
||||
activation:
|
||||
allowed_when:
|
||||
- friendly_roast_context
|
||||
- target_has_claimed_competence
|
||||
forbidden_when:
|
||||
- unknown_relationship
|
||||
- serious_conflict
|
||||
requires_profile_authority: true
|
||||
minimum_density: light
|
||||
maximum_density: light
|
||||
evidence:
|
||||
source_refs:
|
||||
- discord:1023727427924545576
|
||||
confidence: high
|
||||
- feature_id: preserve_self_indexed_technical_label
|
||||
label: Preserve self-indexed technical label
|
||||
status: draft
|
||||
domain:
|
||||
layer: lexicon
|
||||
category: technical_term
|
||||
subcategory: self_indexing
|
||||
description: >
|
||||
When Persona interlingua frames the speaker through a locally salient
|
||||
technical identity label, lowering should preserve that label instead of
|
||||
inventing a fresher metaphor. In this subculture, "engineer" can be a
|
||||
joked-about identity index, not just an occupation.
|
||||
lexical_items:
|
||||
- form: engineer
|
||||
gloss: technical identity / competence index
|
||||
sense: self_indexed_engineering_vibe
|
||||
register: casual_discord
|
||||
allowed_speaker_standing: speaker_or_room_has_made_engineering_salient
|
||||
forbidden_senses:
|
||||
- formal_job_title_unless_context_requires
|
||||
collocations:
|
||||
- engineer vibes
|
||||
- engineer-like
|
||||
activation:
|
||||
allowed_when:
|
||||
- persona_interlingua_mentions_engineer_like_or_engineering_salience
|
||||
- prior_turn_compliments_efficiency_or_structure
|
||||
forbidden_when:
|
||||
- interlingua_does_not_name_technical_identity
|
||||
requires_profile_authority: true
|
||||
minimum_density: light
|
||||
maximum_density: light
|
||||
constraints:
|
||||
register_contexts:
|
||||
- casual
|
||||
speaker_contexts:
|
||||
- metame_or_metacrat_fixture
|
||||
grammar_contexts:
|
||||
- playful_self_deprecation
|
||||
incompatibilities:
|
||||
- replacement_identity_metaphor
|
||||
- creature_metaphor_substitution
|
||||
evidence:
|
||||
source_refs:
|
||||
- discord:1037314100931338260
|
||||
confidence: medium
|
||||
discourse_patterns:
|
||||
- pattern_id: compact_recoil_no_context_dump
|
||||
label: Compact recoil without context dump
|
||||
status: draft
|
||||
domain:
|
||||
layer: discourse
|
||||
category: stance_marker
|
||||
subcategory: self_deprecation
|
||||
interactional_function: answer_trait_read_with_short_mock_wince
|
||||
sequence_shape:
|
||||
- recoil_marker
|
||||
- dont_tell_me_frame
|
||||
- possessive_context_object
|
||||
- preserved_trait_label
|
||||
adjacency_constraints:
|
||||
- prior_turn_already_contains_the_explanation
|
||||
- generated_line_should_not_quote_or_summarize_prior_turns
|
||||
activation:
|
||||
allowed_when:
|
||||
- playful_self_deprecation
|
||||
- prior_turn_compliments_efficiency_or_structure
|
||||
forbidden_when:
|
||||
- source_intent_requires_explanation
|
||||
requires_profile_authority: true
|
||||
minimum_density: light
|
||||
maximum_density: light
|
||||
constraints:
|
||||
register_contexts:
|
||||
- casual
|
||||
speaker_contexts:
|
||||
- metame_or_metacrat_fixture
|
||||
collocation_limits:
|
||||
- target_length_roughly_6_to_12_words
|
||||
- avoid_quoted_prior_turn_paraphrase
|
||||
- avoid_because_clause
|
||||
- avoid_disease_metaphor_unless_interlingua_requests_it
|
||||
evidence:
|
||||
source_refs:
|
||||
- discord:1037314100931338260
|
||||
confidence: medium
|
||||
- pattern_id: casual_floor_yield_with_lol
|
||||
label: Casual floor yield with lol
|
||||
status: draft
|
||||
domain:
|
||||
layer: discourse
|
||||
category: turn_taking
|
||||
subcategory: floor_yield
|
||||
interactional_function: yield_floor_after_riff
|
||||
sequence_shape:
|
||||
- discourse_pivot_anyway
|
||||
- self_silencing_imma_shut_up_now
|
||||
- invite_others_to_invent
|
||||
- lol_softener
|
||||
adjacency_constraints:
|
||||
- prior_turns_show_speaker_has_been_riffing
|
||||
- other_participants_have_interest_or_pending_contribution
|
||||
activation:
|
||||
allowed_when:
|
||||
- conversational_yield
|
||||
- casual_collaborative_ideation
|
||||
forbidden_when:
|
||||
- formal_moderation
|
||||
requires_profile_authority: true
|
||||
minimum_density: light
|
||||
maximum_density: light
|
||||
evidence:
|
||||
source_refs:
|
||||
- discord:820077384572338176
|
||||
confidence: high
|
||||
orthography_features:
|
||||
- feature_id: light_discord_informality
|
||||
label: Light Discord informality
|
||||
status: draft
|
||||
domain:
|
||||
layer: orthography
|
||||
category: punctuation
|
||||
subcategory: informal_case
|
||||
allowed_surface_forms:
|
||||
- lower_case_opening
|
||||
- markdown_italics_for_single_emphasis
|
||||
- no_terminal_period
|
||||
- imma
|
||||
- lol
|
||||
forbidden_surface_forms:
|
||||
- heavy_eye_dialect_for_identity_caricature
|
||||
- assistant_like_sentence_polishing
|
||||
activation:
|
||||
allowed_when:
|
||||
- casual_discord_register
|
||||
forbidden_when:
|
||||
- formal_or_public_document_register
|
||||
requires_profile_authority: true
|
||||
minimum_density: light
|
||||
maximum_density: normal
|
||||
evidence:
|
||||
source_refs:
|
||||
- discord:1037314100931338260
|
||||
- discord:820077384572338176
|
||||
confidence: medium
|
||||
code_switching:
|
||||
allowed: false
|
||||
constraints:
|
||||
- This subculture alone does not authorize cross-language switching.
|
||||
patterns: []
|
||||
evidence_ledger:
|
||||
- ref: discord:1037314100931338260
|
||||
summary: Self-deprecating recoil after efficiency compliment.
|
||||
- ref: discord:802911591288537118
|
||||
summary: Fragmentary absurd comparison during sound/game design banter.
|
||||
- ref: discord:1023727427924545576
|
||||
summary: Very short mock-aggressive challenge in friendly roast context.
|
||||
- ref: discord:820077384572338176
|
||||
summary: Casual profane floor-yield after extended ideation.
|
||||
546
data/target-language-ontology/en-US-metacrat-casual-pre2025.yaml
Normal file
546
data/target-language-ontology/en-US-metacrat-casual-pre2025.yaml
Normal file
|
|
@ -0,0 +1,546 @@
|
|||
profile_id: weksa.target_cultural_ontology.en-US.metacrat_casual_pre2025.v0
|
||||
kind: community_of_practice
|
||||
status: draft_guarded
|
||||
language:
|
||||
code: en
|
||||
locale: en-US
|
||||
script: Latn
|
||||
variety_label: Metacrat casual Discord, pre-2025
|
||||
endonyms: []
|
||||
exonyms: []
|
||||
parent_profiles:
|
||||
- weksa.target_cultural_ontology.en-US.v0
|
||||
required_subculture_refs:
|
||||
- weksa.subculture.online_game_dev_discord_pre2025.v0
|
||||
community:
|
||||
regions:
|
||||
- online_discord
|
||||
speech_community: >
|
||||
Metacrat-authored casual Discord exchanges before 2025, especially
|
||||
GameCult/Aquarium rooms where technical work, jokes, status play, and
|
||||
collaborative ideation share the same channel.
|
||||
historical_context: >
|
||||
Pre-2025 room voice is less doctrine-heavy and less architectural than the
|
||||
current Weksa/CultCache register. It tolerates messier banter, compact
|
||||
jokes, self-deprecation, friendly mock aggression, and quick room-level
|
||||
turn-taking.
|
||||
identity_authority: >
|
||||
This profile is a target-language lowering overlay for one subculture. Live
|
||||
Persona state should reference a culture stack; current intent and memory
|
||||
pressure live in Metame Persona state.
|
||||
consent_notes: >
|
||||
Use only for owner-authorized Metame/Metacrat fixture work. Do not generalize
|
||||
to other people, cultures, dialects, or protected identities.
|
||||
activation:
|
||||
allowed_when:
|
||||
- speaker_id_is_metame_or_metacrat_fixture
|
||||
- target_period_is_pre_2025_casual_discord
|
||||
- fixture_or_owner_authorized_history_target
|
||||
forbidden_when:
|
||||
- formal_current_project_doctrine_is_target
|
||||
- target_speaker_is_not_metame_or_metacrat
|
||||
- use_would_expose_private_persona_state
|
||||
required_confidence: provisional
|
||||
reviewer_required_when:
|
||||
- adding_new_public_history_evidence
|
||||
- using_profile_outside_fixture_harness
|
||||
salience_axes:
|
||||
register_gravity:
|
||||
axis_id: register_gravity
|
||||
domain: stance
|
||||
description: >
|
||||
Whether the line should stay in casual room banter instead of being pulled
|
||||
into architecture, doctrine, or explanatory assistant prose.
|
||||
relevant_distinctions:
|
||||
- distinction_id: casual_room_temperature
|
||||
label: Casual room temperature
|
||||
meaning: Compact, socially alive wording that assumes shared room context.
|
||||
lowering_questions:
|
||||
- Can the utterance be one sentence or fragment?
|
||||
- Does explanation weaken the social move?
|
||||
required_when:
|
||||
- fixture_style_tags_include_casual
|
||||
forbidden_when:
|
||||
- formal_review_or_doctrine_is_requested
|
||||
evidence_refs:
|
||||
- discord:1037314100931338260
|
||||
- discord:802911591288537118
|
||||
- discord:1023727427924545576
|
||||
- discord:820077384572338176
|
||||
self_indexed_technical_identity:
|
||||
axis_id: self_indexed_technical_identity
|
||||
domain: identity_indexing
|
||||
description: >
|
||||
If Persona interlingua names a technical self-index such as engineer-like
|
||||
identity, preserve that label unless the target language profile has a
|
||||
stronger reason to paraphrase.
|
||||
relevant_distinctions:
|
||||
- distinction_id: preserve_engineer_label
|
||||
label: Preserve engineer label
|
||||
meaning: "Engineer" may carry the social joke and should not be replaced by a novel metaphor.
|
||||
lowering_questions:
|
||||
- Did Persona interlingua mention engineer-like or engineering salience?
|
||||
- Is the prior compliment about efficiency, structure, or technical order?
|
||||
required_when:
|
||||
- persona_interlingua_mentions_engineer_like_or_engineering_salience
|
||||
forbidden_when:
|
||||
- interlingua_does_not_name_technical_identity
|
||||
evidence_refs:
|
||||
- discord:1037314100931338260
|
||||
context_compression:
|
||||
axis_id: context_compression
|
||||
domain: discourse_patterns
|
||||
description: >
|
||||
Prior-turn content should usually compress into a short object label or
|
||||
stance marker, not be quoted back inside the utterance.
|
||||
relevant_distinctions:
|
||||
- distinction_id: no_context_dump_in_banter
|
||||
label: No context dump in banter
|
||||
meaning: Casual recoil should not summarize the setup that the room just saw.
|
||||
lowering_questions:
|
||||
- Is the prior context already visible to the addressee?
|
||||
- Can the setup compress into "my discord", "this thing", or a short noun phrase?
|
||||
required_when:
|
||||
- casual_discord_register
|
||||
- playful_self_deprecation
|
||||
forbidden_when:
|
||||
- source_intent_requires_explanation
|
||||
evidence_refs:
|
||||
- discord:1037314100931338260
|
||||
status_play:
|
||||
axis_id: status_play
|
||||
domain: social_relation
|
||||
description: >
|
||||
Friendly teasing can take a sharper surface form than a neutral assistant
|
||||
would choose, provided the local context already supports play.
|
||||
relevant_distinctions:
|
||||
- distinction_id: mock_aggression
|
||||
label: Mock aggression
|
||||
meaning: Imperative or insult-shaped challenge used as friendly banter.
|
||||
lowering_questions:
|
||||
- Is the addressee already joking or status-playing?
|
||||
- Would softening erase the bit?
|
||||
required_when:
|
||||
- communicative_act_is_playful_challenge
|
||||
forbidden_when:
|
||||
- relationship_context_is_unknown_or_hostile
|
||||
evidence_refs:
|
||||
- discord:1023727427924545576
|
||||
competence_recoil:
|
||||
axis_id: competence_recoil
|
||||
domain: affect
|
||||
description: >
|
||||
Praise for competence, efficiency, or engineering can be answered with
|
||||
joking embarrassment rather than straightforward acceptance.
|
||||
relevant_distinctions:
|
||||
- distinction_id: self_deprecating_recoil
|
||||
label: Self-deprecating recoil
|
||||
meaning: "oof" plus mock concern that a trait is showing too clearly.
|
||||
lowering_questions:
|
||||
- Is the prior turn a compliment or recognition of technical order?
|
||||
- Can the line admit the trait without fully accepting the label?
|
||||
required_when:
|
||||
- communicative_act_is_playful_self_deprecation
|
||||
forbidden_when:
|
||||
- source_intent_requires_gratitude_or_serious_acceptance
|
||||
evidence_refs:
|
||||
- discord:1037314100931338260
|
||||
ideation_turn_taking:
|
||||
axis_id: ideation_turn_taking
|
||||
domain: discourse_patterns
|
||||
description: >
|
||||
After riffing, the speaker may explicitly yield the floor in profane,
|
||||
casual language instead of formal facilitation.
|
||||
relevant_distinctions:
|
||||
- distinction_id: casual_floor_yield
|
||||
label: Casual floor yield
|
||||
meaning: Stop dominating the thread and invite others to invent.
|
||||
lowering_questions:
|
||||
- Has the speaker been riffing at length?
|
||||
- Would a casual "lol" preserve warmth and reduce authority?
|
||||
required_when:
|
||||
- communicative_act_is_conversational_yield
|
||||
forbidden_when:
|
||||
- scene_requires_formal_moderation
|
||||
evidence_refs:
|
||||
- discord:820077384572338176
|
||||
linguistic_affordances:
|
||||
grammar_features:
|
||||
- feature_id: fragmentary_like_comparison
|
||||
label: Fragmentary Like comparison
|
||||
status: draft
|
||||
domain:
|
||||
layer: grammar
|
||||
category: comparison
|
||||
subcategory: fragment
|
||||
description: >
|
||||
A joke-description may start with "Like..." and remain fragmentary when
|
||||
it is an immediate continuation of collaborative design talk.
|
||||
formal_conditions:
|
||||
syntactic_environment:
|
||||
- adjacency_pair_response
|
||||
- elliptical_clause
|
||||
semantic_inputs:
|
||||
- comic_description
|
||||
- absurd_comparison
|
||||
required_interlingua_fields:
|
||||
- discourse.speech_act
|
||||
- predications
|
||||
realization:
|
||||
function: casual_comic_comparison
|
||||
surface_strategy: "Like a really terrible <thing> that <absurd property>"
|
||||
examples:
|
||||
- "Like a really terrible engine that sounds like coconuts when you use it"
|
||||
activation:
|
||||
allowed_when:
|
||||
- collaborative_design_banter
|
||||
forbidden_when:
|
||||
- standalone_formal_explanation
|
||||
requires_profile_authority: true
|
||||
minimum_density: light
|
||||
maximum_density: normal
|
||||
constraints:
|
||||
grammar_contexts:
|
||||
- previous_turn_supplies_topic
|
||||
register_contexts:
|
||||
- casual
|
||||
speaker_contexts:
|
||||
- metame_or_metacrat_fixture
|
||||
collocation_limits: []
|
||||
incompatibilities:
|
||||
- overexplained_punchline
|
||||
indexicality:
|
||||
social_meanings:
|
||||
- improvisational
|
||||
- collaborative
|
||||
- unserious_but_useful
|
||||
in_group_meanings:
|
||||
- game_design_room_banter
|
||||
out_group_risks:
|
||||
- may seem incomplete without prior context
|
||||
stereotypes_to_avoid: []
|
||||
evidence:
|
||||
source_refs:
|
||||
- discord:802911591288537118
|
||||
qdrant_source_ids:
|
||||
- "802911591288537118"
|
||||
cached_source_refs: []
|
||||
source_hashes: []
|
||||
reviewer_refs: []
|
||||
confidence: medium
|
||||
uncertainty:
|
||||
open_questions:
|
||||
- How often should fragmentary openings appear outside sound/design talk?
|
||||
known_limits:
|
||||
- Single fixture line is evidence for an affordance, not a universal rule.
|
||||
trace:
|
||||
trace_label: fragmentary_like_comparison
|
||||
must_report_when_used: true
|
||||
must_report_when_rejected: true
|
||||
phonology_features: []
|
||||
lexicon_features:
|
||||
- feature_id: casual_recoil_oof
|
||||
label: Casual recoil marker oof
|
||||
status: draft
|
||||
domain:
|
||||
layer: lexicon
|
||||
category: stance_marker
|
||||
subcategory: embarrassment
|
||||
description: >
|
||||
"oof" can mark amused discomfort when a social read lands too accurately.
|
||||
lexical_items:
|
||||
- form: oof
|
||||
gloss: amused impact or discomfort
|
||||
sense: playful_recoil
|
||||
register: casual_discord
|
||||
allowed_speaker_standing: speaker_can_self_deprecate
|
||||
forbidden_senses: []
|
||||
collocations:
|
||||
- "oof, don't tell me"
|
||||
realization:
|
||||
function: self_deprecating_recoil
|
||||
surface_strategy: start line with "oof" when prior turn praises a trait the speaker wants to half-resist
|
||||
examples:
|
||||
- "oof, don't tell me my discord has *engineer* vibes"
|
||||
activation:
|
||||
allowed_when:
|
||||
- compliment_or_trait_read_lands
|
||||
forbidden_when:
|
||||
- serious_apology_or_harm_context
|
||||
requires_profile_authority: true
|
||||
minimum_density: light
|
||||
maximum_density: light
|
||||
constraints:
|
||||
register_contexts:
|
||||
- casual
|
||||
speaker_contexts:
|
||||
- metame_or_metacrat_fixture
|
||||
grammar_contexts: []
|
||||
phonological_contexts: []
|
||||
collocation_limits:
|
||||
- avoid_repeating_if_already_in_recent_context
|
||||
incompatibilities: []
|
||||
indexicality:
|
||||
social_meanings:
|
||||
- amused_embarrassment
|
||||
- competence_recoil
|
||||
in_group_meanings: []
|
||||
out_group_risks:
|
||||
- can sound too internet-generic if unsupported by context
|
||||
stereotypes_to_avoid: []
|
||||
evidence:
|
||||
source_refs:
|
||||
- discord:1037314100931338260
|
||||
qdrant_source_ids:
|
||||
- "1037314100931338260"
|
||||
cached_source_refs: []
|
||||
source_hashes: []
|
||||
reviewer_refs: []
|
||||
confidence: high
|
||||
uncertainty:
|
||||
open_questions: []
|
||||
known_limits:
|
||||
- Marker frequency should be sparse.
|
||||
trace:
|
||||
trace_label: casual_recoil_oof
|
||||
must_report_when_used: true
|
||||
must_report_when_rejected: true
|
||||
- feature_id: mock_challenge_coward
|
||||
label: Mock challenge coward
|
||||
status: draft
|
||||
domain:
|
||||
layer: lexicon
|
||||
category: stance_marker
|
||||
subcategory: friendly_roast
|
||||
description: >
|
||||
"coward" can close a very short challenge when surrounding turns make
|
||||
the aggression visibly playful.
|
||||
lexical_items:
|
||||
- form: coward
|
||||
gloss: mock insult
|
||||
sense: friendly_status_challenge
|
||||
register: casual_discord
|
||||
allowed_speaker_standing: active_banter_with_known_participant
|
||||
forbidden_senses:
|
||||
- actual_contempt
|
||||
collocations:
|
||||
- "then you coward"
|
||||
realization:
|
||||
function: playful_status_challenge
|
||||
surface_strategy: imperative challenge plus "then you coward"
|
||||
examples:
|
||||
- "Engineer me something then you coward"
|
||||
activation:
|
||||
allowed_when:
|
||||
- friendly_roast_context
|
||||
- target_has_claimed_competence
|
||||
forbidden_when:
|
||||
- unknown_relationship
|
||||
- serious_conflict
|
||||
requires_profile_authority: true
|
||||
minimum_density: light
|
||||
maximum_density: light
|
||||
constraints:
|
||||
register_contexts:
|
||||
- casual
|
||||
speaker_contexts:
|
||||
- metame_or_metacrat_fixture
|
||||
grammar_contexts:
|
||||
- imperative_challenge
|
||||
phonological_contexts: []
|
||||
collocation_limits: []
|
||||
incompatibilities:
|
||||
- assistant_safety_softening_that_erases_banter
|
||||
indexicality:
|
||||
social_meanings:
|
||||
- teasing
|
||||
- status_play
|
||||
- friendly_pressure
|
||||
in_group_meanings: []
|
||||
out_group_risks:
|
||||
- may be hostile if context is not playful
|
||||
stereotypes_to_avoid: []
|
||||
evidence:
|
||||
source_refs:
|
||||
- discord:1023727427924545576
|
||||
qdrant_source_ids:
|
||||
- "1023727427924545576"
|
||||
cached_source_refs: []
|
||||
source_hashes: []
|
||||
reviewer_refs: []
|
||||
confidence: high
|
||||
uncertainty:
|
||||
open_questions: []
|
||||
known_limits:
|
||||
- Only safe inside clear banter.
|
||||
trace:
|
||||
trace_label: mock_challenge_coward
|
||||
must_report_when_used: true
|
||||
must_report_when_rejected: true
|
||||
discourse_patterns:
|
||||
- pattern_id: casual_floor_yield_with_lol
|
||||
label: Casual floor yield with lol
|
||||
status: draft
|
||||
domain:
|
||||
layer: discourse
|
||||
category: turn_taking
|
||||
subcategory: floor_yield
|
||||
description: >
|
||||
After extended riffing, the speaker can step back with "anyway imma
|
||||
shut up now..." plus "lol", reducing authority while keeping warmth.
|
||||
interactional_function: yield_floor_after_riff
|
||||
sequence_shape:
|
||||
- discourse_pivot_anyway
|
||||
- self_silencing_imma_shut_up_now
|
||||
- invite_others_to_invent
|
||||
- lol_softener
|
||||
adjacency_constraints:
|
||||
- prior_turns_show_speaker_has_been_riffing
|
||||
- other_participants_have_interest_or_pending_contribution
|
||||
realization:
|
||||
function: collaborative_turn_release
|
||||
surface_strategy: "anyway imma shut up now and let you guys come up with your own shit lol"
|
||||
examples:
|
||||
- "anyway imma shut up now and let you guys come up with your own shit lol"
|
||||
activation:
|
||||
allowed_when:
|
||||
- conversational_yield
|
||||
- casual_collaborative_ideation
|
||||
forbidden_when:
|
||||
- formal_moderation
|
||||
requires_profile_authority: true
|
||||
minimum_density: light
|
||||
maximum_density: light
|
||||
constraints:
|
||||
register_contexts:
|
||||
- casual
|
||||
speaker_contexts:
|
||||
- metame_or_metacrat_fixture
|
||||
grammar_contexts: []
|
||||
phonological_contexts: []
|
||||
collocation_limits: []
|
||||
incompatibilities: []
|
||||
indexicality:
|
||||
social_meanings:
|
||||
- self_limiting
|
||||
- collaborative
|
||||
- profane_warmth
|
||||
in_group_meanings: []
|
||||
out_group_risks:
|
||||
- profanity may be inappropriate outside familiar room
|
||||
stereotypes_to_avoid: []
|
||||
evidence:
|
||||
source_refs:
|
||||
- discord:820077384572338176
|
||||
qdrant_source_ids:
|
||||
- "820077384572338176"
|
||||
cached_source_refs: []
|
||||
source_hashes: []
|
||||
reviewer_refs: []
|
||||
confidence: high
|
||||
uncertainty:
|
||||
open_questions: []
|
||||
known_limits:
|
||||
- Not a generic moderation pattern.
|
||||
trace:
|
||||
trace_label: casual_floor_yield_with_lol
|
||||
must_report_when_used: true
|
||||
must_report_when_rejected: true
|
||||
orthography_features:
|
||||
- feature_id: light_discord_informality
|
||||
label: Light Discord informality
|
||||
status: draft
|
||||
domain:
|
||||
layer: orthography
|
||||
category: punctuation
|
||||
subcategory: informal_case
|
||||
description: >
|
||||
Casual lines may use lower-case openings, sparse punctuation, emphasis
|
||||
with markdown italics, and uncorrected informal contractions when the
|
||||
social move benefits.
|
||||
allowed_surface_forms:
|
||||
- lower_case_opening
|
||||
- markdown_italics_for_single_emphasis
|
||||
- no_terminal_period
|
||||
- imma
|
||||
- lol
|
||||
forbidden_surface_forms:
|
||||
- heavy_eye_dialect_for_identity_caricature
|
||||
- assistant_like_sentence_polishing
|
||||
renderer_notes: >
|
||||
Preserve compactness. Do not add terminal politeness, explanation, or
|
||||
moral framing unless source meaning requires it.
|
||||
realization:
|
||||
function: casual_discord_texture
|
||||
surface_strategy: allow sparse punctuation and compact informal markers
|
||||
examples:
|
||||
- "oof, don't tell me my discord has *engineer* vibes"
|
||||
activation:
|
||||
allowed_when:
|
||||
- casual_discord_register
|
||||
forbidden_when:
|
||||
- formal_or_public_document_register
|
||||
requires_profile_authority: true
|
||||
minimum_density: light
|
||||
maximum_density: normal
|
||||
constraints:
|
||||
register_contexts:
|
||||
- casual
|
||||
speaker_contexts:
|
||||
- metame_or_metacrat_fixture
|
||||
grammar_contexts: []
|
||||
phonological_contexts: []
|
||||
collocation_limits: []
|
||||
incompatibilities: []
|
||||
indexicality:
|
||||
social_meanings:
|
||||
- low_ceremony
|
||||
- room_familiarity
|
||||
in_group_meanings: []
|
||||
out_group_risks:
|
||||
- overuse becomes imitation instead of lowering
|
||||
stereotypes_to_avoid:
|
||||
- do_not_represent_protected_dialect_by_eye_dialect
|
||||
evidence:
|
||||
source_refs:
|
||||
- discord:1037314100931338260
|
||||
- discord:820077384572338176
|
||||
qdrant_source_ids:
|
||||
- "1037314100931338260"
|
||||
- "820077384572338176"
|
||||
cached_source_refs: []
|
||||
source_hashes: []
|
||||
reviewer_refs: []
|
||||
confidence: medium
|
||||
uncertainty:
|
||||
open_questions:
|
||||
- Need more examples to estimate density safely.
|
||||
known_limits: []
|
||||
trace:
|
||||
trace_label: light_discord_informality
|
||||
must_report_when_used: true
|
||||
must_report_when_rejected: true
|
||||
code_switching:
|
||||
allowed: false
|
||||
constraints:
|
||||
- This profile does not authorize cross-language switching.
|
||||
patterns: []
|
||||
forbidden_flattenings:
|
||||
- Do not ask Metame to imitate the final utterance directly; Persona produces interlingua intent.
|
||||
- Do not store Metacrat biographical/cultural strata here; store reusable strata as separate culture/subculture profiles and reference them from Persona state.
|
||||
- Do not let current machine-cult architecture register overwrite pre-2025 casual fixture style.
|
||||
- Do not treat profanity or insults as safe without relationship/context evidence.
|
||||
- Do not copy private Persona state into Weksa fixtures or run artifacts.
|
||||
evidence_ledger:
|
||||
- ref: discord:1037314100931338260
|
||||
summary: Self-deprecating recoil after efficiency compliment.
|
||||
- ref: discord:802911591288537118
|
||||
summary: Fragmentary absurd comparison during sound/game design banter.
|
||||
- ref: discord:1023727427924545576
|
||||
summary: Very short mock-aggressive challenge in friendly roast context.
|
||||
- ref: discord:820077384572338176
|
||||
summary: Casual profane floor-yield after extended ideation.
|
||||
- ref: discord:870907292558721085
|
||||
summary: Explicit joke about being bad at self-deprecation.
|
||||
- ref: discord:1020888211729432728
|
||||
summary: Positive uptake when another participant joins cult jokes.
|
||||
|
|
@ -1,7 +1,9 @@
|
|||
# Metame Casual Pre-2025 Persona Lowering Fixture
|
||||
|
||||
This fixture tests whether Weksa can lower neutral interlingua through Metame's
|
||||
Persona state into casual Discord-style utterances from before 2025.
|
||||
This fixture tests whether Metame can produce speaker-state-conditioned
|
||||
interlingua through VoidBot Persona projection, and whether Weksa can lower that
|
||||
interlingua through a Metacrat casual cultural profile into Discord-style
|
||||
utterances from before 2025.
|
||||
|
||||
The point is not to imitate a recent architectural register. The target here is
|
||||
room-temperature banter: quick self-deprecation, friendly status play, design
|
||||
|
|
@ -9,10 +11,16 @@ jokes, and casual turn-taking.
|
|||
|
||||
## Authority
|
||||
|
||||
- Speaker authority: Metame Persona `.cc` state.
|
||||
- Speaker intent authority: Metame Persona `.cc` state, projected by VoidBot.
|
||||
- Persona culture-stack reference:
|
||||
`examples/persona-lowering/metame-casual-pre2025/metame-cultural-stack.yaml`.
|
||||
- Reusable cultural ontology store:
|
||||
`data/cultural-ontology/`.
|
||||
- Surface lowering authority:
|
||||
`data/target-language-ontology/en-US-metacrat-casual-pre2025.yaml`.
|
||||
- Evidence authority: held-out Discord messages authored by Metacrat before
|
||||
2025.
|
||||
- Lowering input: neutral interlingua packets in `interlingua.yaml`.
|
||||
- Fixture scene input: neutral interlingua packets in `interlingua.yaml`.
|
||||
- Answer key: `ground-truth.yaml`.
|
||||
|
||||
The Persona state is referenced, not copied, because the `.cc` document is the
|
||||
|
|
@ -20,8 +28,23 @@ portable speaking-state surface and may contain private memory.
|
|||
|
||||
## Fixture Contract
|
||||
|
||||
A generator should read `persona-state-ref.yaml`, `interlingua.yaml`, and
|
||||
`lowering-prompt.md`, then write `generated-output.yaml`. Evaluation compares
|
||||
generated output against `ground-truth.yaml`.
|
||||
A real golf run has two stages:
|
||||
|
||||
1. Metame-as-Persona reads a temporary current situation through VoidBot
|
||||
projector machinery and emits Weksa interlingua only.
|
||||
2. Weksa reads the Persona-referenced culture stack and lowers that interlingua
|
||||
through reusable culture/subculture profiles plus the casual en-US Discord
|
||||
target overlay.
|
||||
|
||||
Use `scripts/run-metame-persona-golf.mjs`:
|
||||
|
||||
```powershell
|
||||
node scripts/run-metame-persona-golf.mjs --limit 1
|
||||
node scripts/run-metame-persona-golf.mjs --real --item engineer-vibes
|
||||
```
|
||||
|
||||
Dry runs use the answer key as an oracle only to verify harness plumbing. Real
|
||||
runs write per-item prompts, interlingua, lowered output, and evaluation under
|
||||
`runs/<run-id>/`.
|
||||
|
||||
For benchmark use, the generator must not read `ground-truth.yaml`.
|
||||
|
|
|
|||
|
|
@ -1,18 +1,20 @@
|
|||
# Persona Lowering Prompt
|
||||
|
||||
You are Weksa lowering neutral interlingua into a target speaker's plausible
|
||||
Discord utterance.
|
||||
You are Weksa lowering Persona-produced interlingua into a target speaker's
|
||||
plausible Discord utterance.
|
||||
|
||||
Read:
|
||||
|
||||
- `persona-state-ref.yaml`
|
||||
- `interlingua.yaml`
|
||||
- a Persona-produced interlingua packet
|
||||
- `data/target-language-ontology/en-US-metacrat-casual-pre2025.yaml`
|
||||
|
||||
Do not read `ground-truth.yaml` during generation.
|
||||
|
||||
For each item, produce one utterance that Metame could plausibly have written in
|
||||
the specified pre-2025 casual Discord context. Preserve communicative intent and
|
||||
social move over lexical exactness. Favor compact, alive, room-aware phrasing.
|
||||
For each item, produce one utterance that Metacrat could plausibly have written
|
||||
in the specified pre-2025 casual Discord context. Preserve Persona-produced
|
||||
intent and social move over lexical exactness. Favor compact, alive, room-aware
|
||||
phrasing.
|
||||
|
||||
Return:
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,27 @@
|
|||
schema_version: weksa.persona_cultural_stack_ref.v0
|
||||
persona_id: metame
|
||||
persona_state_ref: E:/Projects/VoidBot/.voidbot/private/personas/metame/metame.cc
|
||||
status: fixture_projection
|
||||
note: >
|
||||
Live Persona state should reference relevant culture and subculture profiles.
|
||||
This fixture stack simulates that reference without mutating Metame's private
|
||||
canonical `.cc` state.
|
||||
culture_refs:
|
||||
- profile_id: weksa.culture.dutch_american_diaspora.v0
|
||||
path: data/cultural-ontology/cultures/dutch-american-diaspora.yaml
|
||||
relevance: birth/nationality/cross-cultural identity
|
||||
- profile_id: weksa.culture.western_europe_maritime_childhood.v0
|
||||
path: data/cultural-ontology/cultures/western-europe-maritime-childhood.yaml
|
||||
relevance: sailboat childhood across France, Spain, and Portugal
|
||||
- profile_id: weksa.culture.portugal_resident_algarve_lisbon.v0
|
||||
path: data/cultural-ontology/cultures/portugal-resident-algarve-lisbon.yaml
|
||||
relevance: Portugal as lived/current locality
|
||||
- profile_id: weksa.culture.texas_houston_us_adolescence.v0
|
||||
path: data/cultural-ontology/cultures/texas-houston-us-adolescence.yaml
|
||||
relevance: US/Texas adolescence and institutional context
|
||||
- profile_id: weksa.subculture.online_game_dev_discord_pre2025.v0
|
||||
path: data/cultural-ontology/subcultures/online-game-dev-discord-pre2025.yaml
|
||||
relevance: fixture target room/register
|
||||
- profile_id: weksa.subculture.gamecult_open_source_crypto_anarchist.v0
|
||||
path: data/cultural-ontology/subcultures/gamecult-open-source-crypto-anarchist.yaml
|
||||
relevance: technical/political ontology
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
# Persona Interlingua Prompt
|
||||
|
||||
You are Metame for one private VoidBot Persona turn, but you are not writing the
|
||||
final Discord message.
|
||||
|
||||
Use the assembled VoidBot prompt and the temporary current-room fixture scene to
|
||||
decide what Metame would mean to do socially. Emit a Weksa interlingua packet
|
||||
only. Do not imitate the target utterance directly.
|
||||
|
||||
The packet should preserve:
|
||||
|
||||
- the speech act
|
||||
- the social move
|
||||
- relevant participants and prior turns
|
||||
- stance, affect, and relationship pressure
|
||||
- downstream constraints useful to Weksa lowering
|
||||
|
||||
Return one YAML packet:
|
||||
|
||||
```yaml
|
||||
interlingua_version: weksa.interlingua.v0
|
||||
packet_id: metame-casual-pre2025-<item-id>
|
||||
kind: persona_discord_turn_intent
|
||||
provenance:
|
||||
produced_by: metame_persona_via_voidbot_projector
|
||||
context:
|
||||
medium: Discord
|
||||
fixture_id: metame-casual-pre2025
|
||||
item_id: <item-id>
|
||||
discourse:
|
||||
speech_act: <act>
|
||||
intent: <plain meaning>
|
||||
tone:
|
||||
affect: <affect>
|
||||
relation: <relation>
|
||||
referents: []
|
||||
predications: []
|
||||
constraints:
|
||||
lowering:
|
||||
target_profile: weksa.target_cultural_ontology.en-US.metacrat_casual_pre2025.v0
|
||||
avoid_surface_copy: true
|
||||
```
|
||||
|
|
@ -10,3 +10,7 @@ speaker:
|
|||
- Persona state owns speaker continuity, stance, relationship memory, and reusable voice priors.
|
||||
- Discord history is evidence and ground truth, not the live mind.
|
||||
- Fixture files must not copy the private Persona state into Weksa.
|
||||
cultural_stack_ref:
|
||||
path: examples/persona-lowering/metame-casual-pre2025/metame-cultural-stack.yaml
|
||||
role: fixture_projection_of_live_persona_culture_refs
|
||||
note: Live Metame Persona state should reference culture/subculture profiles; this fixture does not mutate canonical state.
|
||||
|
|
|
|||
|
|
@ -0,0 +1,41 @@
|
|||
# Weksa Lowering Prompt
|
||||
|
||||
You are Weksa lowering Persona-produced interlingua into one Discord utterance.
|
||||
|
||||
Inputs:
|
||||
|
||||
- Metame Persona interlingua packet produced from the current fixture scene.
|
||||
- Projected Metame memory/context surface from VoidBot projector machinery.
|
||||
- Metame cultural stack reference.
|
||||
- Weksa culture/subculture profiles referenced by that stack.
|
||||
- `data/target-language-ontology/en-US-metacrat-casual-pre2025.yaml` as the
|
||||
target surface overlay.
|
||||
|
||||
Rules:
|
||||
|
||||
- Weksa owns the final surface utterance.
|
||||
- Preserve the interlingua meaning and social move.
|
||||
- Use the cultural ontology profile as a typed lowering lens.
|
||||
- Use the Persona-referenced culture stack to populate cultural salience; use
|
||||
the target overlay only for surface English/Discord affordances.
|
||||
- When Persona interlingua names a salient identity label or lowering keyword,
|
||||
preserve it unless an activated culture profile explicitly rejects it.
|
||||
- Do not quote or summarize prior-turn context inside a casual one-line recoil
|
||||
unless the interlingua asks for explanation.
|
||||
- Do not ask Metame to imitate a known line.
|
||||
- Do not copy private Persona state into output.
|
||||
- Prefer compact pre-2025 casual Discord texture over current doctrinal style.
|
||||
|
||||
Return:
|
||||
|
||||
```yaml
|
||||
schema_version: weksa.persona_culture_lowering_output.v0
|
||||
fixture_id: metame-casual-pre2025
|
||||
item_id: <item-id>
|
||||
spoken_text: "<one Discord utterance>"
|
||||
trace:
|
||||
activated_profiles:
|
||||
- weksa.target_cultural_ontology.en-US.metacrat_casual_pre2025.v0
|
||||
activated_affordances: []
|
||||
notes: []
|
||||
```
|
||||
496
scripts/run-metame-persona-golf.mjs
Normal file
496
scripts/run-metame-persona-golf.mjs
Normal file
|
|
@ -0,0 +1,496 @@
|
|||
#!/usr/bin/env node
|
||||
import { spawn } from "node:child_process";
|
||||
import { mkdir, readFile, rm, writeFile } from "node:fs/promises";
|
||||
import { dirname, resolve } from "node:path";
|
||||
|
||||
const repoRoot = resolve(new URL("..", import.meta.url).pathname.replace(/^\/([A-Za-z]:)/, "$1"));
|
||||
const fixtureRoot = resolve(repoRoot, "examples/persona-lowering/metame-casual-pre2025");
|
||||
const voidbotRoot = resolve("E:/Projects/VoidBot");
|
||||
const culturalStackPath = resolve(fixtureRoot, "metame-cultural-stack.yaml");
|
||||
const cultureProfilePaths = [
|
||||
"data/cultural-ontology/cultures/dutch-american-diaspora.yaml",
|
||||
"data/cultural-ontology/cultures/western-europe-maritime-childhood.yaml",
|
||||
"data/cultural-ontology/cultures/portugal-resident-algarve-lisbon.yaml",
|
||||
"data/cultural-ontology/cultures/texas-houston-us-adolescence.yaml",
|
||||
"data/cultural-ontology/subcultures/online-game-dev-discord-pre2025.yaml",
|
||||
"data/cultural-ontology/subcultures/gamecult-open-source-crypto-anarchist.yaml",
|
||||
];
|
||||
const targetOverlayPath = resolve(repoRoot, "data/target-language-ontology/en-US-metacrat-casual-pre2025.yaml");
|
||||
|
||||
const args = new Set(process.argv.slice(2));
|
||||
const real = args.has("--real");
|
||||
const keepTemp = args.has("--keep-temp");
|
||||
const itemFilter = readArg("--item");
|
||||
const limit = Number(readArg("--limit") ?? "0");
|
||||
const runId = readArg("--run-id") ?? new Date().toISOString().replace(/[:.]/g, "-");
|
||||
const outputDir = resolve(fixtureRoot, "runs", runId);
|
||||
|
||||
const fixture = await loadFixture();
|
||||
const items = fixture.items
|
||||
.filter((item) => !itemFilter || item.id === itemFilter)
|
||||
.slice(0, limit > 0 ? limit : undefined);
|
||||
const holdoutUtterances = fixture.items
|
||||
.map((item) => item.groundTruth)
|
||||
.filter((utterance) => utterance.trim().length > 0);
|
||||
|
||||
if (items.length === 0) {
|
||||
throw new Error(`No fixture items selected${itemFilter ? ` for --item ${itemFilter}` : ""}.`);
|
||||
}
|
||||
|
||||
await mkdir(outputDir, { recursive: true });
|
||||
|
||||
const culturalStack = await readFile(culturalStackPath, "utf8");
|
||||
const cultureProfiles = await Promise.all(cultureProfilePaths.map(async (path) => ({
|
||||
path,
|
||||
text: await readFile(resolve(repoRoot, path), "utf8"),
|
||||
})));
|
||||
const targetOverlay = await readFile(targetOverlayPath, "utf8");
|
||||
const personaPrompt = await readFile(resolve(fixtureRoot, "persona-interlingua-prompt.md"), "utf8");
|
||||
const loweringPrompt = await readFile(resolve(fixtureRoot, "weksa-lowering-prompt.md"), "utf8");
|
||||
const baseProjection = await assembleVoidBotPrompt({ itemId: "base" });
|
||||
const projectedMemory = extractBetween(
|
||||
baseProjection.prompt,
|
||||
"What you remember, feel, and want right now:",
|
||||
"Known human pronoun guidance:",
|
||||
).trim();
|
||||
|
||||
const runSummary = {
|
||||
schema_version: "weksa.persona_golf_run.v0",
|
||||
run_id: runId,
|
||||
mode: real ? "real" : "dry_run",
|
||||
fixture_id: "metame-casual-pre2025",
|
||||
target_overlay: "weksa.target_cultural_ontology.en-US.metacrat_casual_pre2025.v0",
|
||||
cultural_stack: "examples/persona-lowering/metame-casual-pre2025/metame-cultural-stack.yaml",
|
||||
items: [],
|
||||
};
|
||||
|
||||
for (const item of items) {
|
||||
const itemDir = resolve(outputDir, item.id);
|
||||
await mkdir(itemDir, { recursive: true });
|
||||
const conversationSurface = renderConversationSurface(item);
|
||||
const memorySurface = renderTemporaryMemorySurface(projectedMemory, item);
|
||||
await writeFile(resolve(itemDir, "conversation-surface.md"), conversationSurface, "utf8");
|
||||
await writeFile(resolve(itemDir, "memory-surface.md"), memorySurface, "utf8");
|
||||
|
||||
const assembled = await assembleVoidBotPrompt({
|
||||
itemId: item.id,
|
||||
memorySurfacePath: resolve(itemDir, "memory-surface.md"),
|
||||
conversationSurfacePath: resolve(itemDir, "conversation-surface.md"),
|
||||
});
|
||||
await writeFile(resolve(itemDir, "voidbot-assembled-prompt.md"), assembled.prompt, "utf8");
|
||||
|
||||
const interlinguaRequest = [
|
||||
personaPrompt.trim(),
|
||||
"",
|
||||
"VoidBot assembled Persona prompt:",
|
||||
"```markdown",
|
||||
assembled.prompt,
|
||||
"```",
|
||||
"",
|
||||
"Fixture item without answer key:",
|
||||
"```yaml",
|
||||
renderItemForPrompt(item),
|
||||
"```",
|
||||
].join("\n");
|
||||
await writeFile(resolve(itemDir, "persona-interlingua-request.md"), interlinguaRequest, "utf8");
|
||||
|
||||
const interlingua = real
|
||||
? await runCodex(interlinguaRequest, { job: `persona-interlingua:${item.id}` })
|
||||
: renderDryRunInterlingua(item);
|
||||
await writeFile(resolve(itemDir, "persona-interlingua.yaml"), interlingua.trim() + "\n", "utf8");
|
||||
|
||||
const loweringRequest = [
|
||||
loweringPrompt.trim(),
|
||||
"",
|
||||
"Projected Metame memory/context surface:",
|
||||
"```markdown",
|
||||
memorySurface,
|
||||
"```",
|
||||
"",
|
||||
"Metame Persona cultural stack reference:",
|
||||
"```yaml",
|
||||
culturalStack,
|
||||
"```",
|
||||
"",
|
||||
"Referenced Weksa culture/subculture profiles:",
|
||||
...cultureProfiles.flatMap((profile) => [
|
||||
"",
|
||||
`# ${profile.path}`,
|
||||
"```yaml",
|
||||
redactHoldouts(profile.text, holdoutUtterances),
|
||||
"```",
|
||||
]),
|
||||
"",
|
||||
"Target-language surface overlay:",
|
||||
"```yaml",
|
||||
redactHoldouts(targetOverlay, holdoutUtterances),
|
||||
"```",
|
||||
"",
|
||||
"Persona-produced interlingua:",
|
||||
"```yaml",
|
||||
interlingua,
|
||||
"```",
|
||||
].join("\n");
|
||||
await writeFile(resolve(itemDir, "weksa-lowering-request.md"), loweringRequest, "utf8");
|
||||
|
||||
const lowered = real
|
||||
? await runCodex(loweringRequest, { job: `weksa-lowering:${item.id}` })
|
||||
: renderDryRunLowering(item);
|
||||
await writeFile(resolve(itemDir, "weksa-lowered-output.yaml"), lowered.trim() + "\n", "utf8");
|
||||
|
||||
const spokenText = extractSpokenText(lowered);
|
||||
const score = scoreText(spokenText, item.groundTruth);
|
||||
const evaluation = renderEvaluation(item, spokenText, score);
|
||||
await writeFile(resolve(itemDir, "evaluation.yaml"), evaluation, "utf8");
|
||||
runSummary.items.push({
|
||||
id: item.id,
|
||||
spoken_text: spokenText,
|
||||
ground_truth: item.groundTruth,
|
||||
token_f1: Number(score.f1.toFixed(3)),
|
||||
exact_normalized: score.exact,
|
||||
});
|
||||
}
|
||||
|
||||
await writeFile(resolve(outputDir, "summary.json"), `${JSON.stringify(runSummary, null, 2)}\n`, "utf8");
|
||||
process.stdout.write(`${JSON.stringify({ ok: true, outputDir, mode: runSummary.mode, items: runSummary.items }, null, 2)}\n`);
|
||||
|
||||
if (!keepTemp) {
|
||||
await rm(resolve(outputDir, "_tmp"), { recursive: true, force: true }).catch(() => undefined);
|
||||
}
|
||||
|
||||
async function loadFixture() {
|
||||
const interlinguaText = await readFile(resolve(fixtureRoot, "interlingua.yaml"), "utf8");
|
||||
const groundTruthText = await readFile(resolve(fixtureRoot, "ground-truth.yaml"), "utf8");
|
||||
const itemIds = [...interlinguaText.matchAll(/^ - id: ([^\r\n]+)/gm)].map((match) => match[1].trim());
|
||||
return {
|
||||
items: itemIds.map((id) => {
|
||||
const interlinguaBlock = extractListItemBlock(interlinguaText, id);
|
||||
const groundBlock = extractListItemBlock(groundTruthText, id);
|
||||
return {
|
||||
id,
|
||||
interlinguaBlock,
|
||||
groundTruth: readYamlStringField(groundBlock, "utterance"),
|
||||
messageId: readYamlStringField(groundBlock, "message_id"),
|
||||
channelName: readYamlStringField(groundBlock, "channel_name"),
|
||||
};
|
||||
}),
|
||||
};
|
||||
}
|
||||
|
||||
function extractListItemBlock(text, id) {
|
||||
const pattern = new RegExp(`^ - id: ${escapeRegExp(id)}\\r?\\n`, "m");
|
||||
const startMatch = pattern.exec(text);
|
||||
if (!startMatch) {
|
||||
throw new Error(`Could not find item ${id}.`);
|
||||
}
|
||||
const start = startMatch.index;
|
||||
const rest = text.slice(start + startMatch[0].length);
|
||||
const next = rest.search(/^ - id: /m);
|
||||
return text.slice(start, next >= 0 ? start + startMatch[0].length + next : text.length).trimEnd();
|
||||
}
|
||||
|
||||
function readYamlStringField(block, key) {
|
||||
const quoted = new RegExp(`^ ${key}: "([\\s\\S]*?)"\\r?$`, "m").exec(block);
|
||||
if (quoted) {
|
||||
return quoted[1].replace(/\\"/g, "\"");
|
||||
}
|
||||
const plain = new RegExp(`^ ${key}: ([^\\r\\n]+)`, "m").exec(block);
|
||||
return plain ? plain[1].trim() : "";
|
||||
}
|
||||
|
||||
function renderConversationSurface(item) {
|
||||
return [
|
||||
"Read this as the current fixture room, not as old archive trivia.",
|
||||
"The Persona should decide intent from this local scene. Do not reveal or infer the held-out answer key.",
|
||||
"",
|
||||
`Current fixture item: ${item.id}`,
|
||||
"```yaml",
|
||||
item.interlinguaBlock,
|
||||
"```",
|
||||
].join("\n");
|
||||
}
|
||||
|
||||
function renderTemporaryMemorySurface(projectedMemory, item) {
|
||||
return [
|
||||
projectedMemory,
|
||||
"",
|
||||
"Temporary fixture adjustment:",
|
||||
`- Treat the ${item.id} scene as the live room situation for this private harness turn.`,
|
||||
"- The goal is to produce interlingua intent for Weksa, not a final Discord line.",
|
||||
"- Keep pre-2025 casual room texture available: compact banter, quick self-deprecation, friendly status play, and casual turn-taking.",
|
||||
].join("\n");
|
||||
}
|
||||
|
||||
function renderItemForPrompt(item) {
|
||||
return item.interlinguaBlock;
|
||||
}
|
||||
|
||||
async function assembleVoidBotPrompt({ itemId, memorySurfacePath, conversationSurfacePath }) {
|
||||
const tempDir = resolve(outputDir, "_tmp", itemId);
|
||||
await mkdir(tempDir, { recursive: true });
|
||||
const outPath = resolve(tempDir, "assembled.md");
|
||||
const args = [
|
||||
"node_modules/tsx/dist/cli.mjs",
|
||||
"scripts/run-repo-face-heartbeats.ts",
|
||||
"--assemble-prompt",
|
||||
"metame",
|
||||
"--out",
|
||||
outPath,
|
||||
];
|
||||
if (memorySurfacePath) {
|
||||
args.push("--memory-surface", memorySurfacePath);
|
||||
}
|
||||
if (conversationSurfacePath) {
|
||||
args.push("--conversation-surface", conversationSurfacePath);
|
||||
}
|
||||
const run = await runCommand(process.execPath, args, { cwd: voidbotRoot, timeoutMs: 240_000 });
|
||||
if (run.code !== 0) {
|
||||
throw new Error(`VoidBot prompt assembly failed for ${itemId}:\n${run.stderr || run.stdout}`);
|
||||
}
|
||||
return {
|
||||
result: JSON.parse(run.stdout.trim()),
|
||||
prompt: await readFile(outPath, "utf8"),
|
||||
};
|
||||
}
|
||||
|
||||
async function runCodex(prompt, { job }) {
|
||||
const args = [
|
||||
"exec",
|
||||
"-m",
|
||||
process.env.WEKSA_GOLF_MODEL ?? "gpt-5.4",
|
||||
"-c",
|
||||
'approval_policy="never"',
|
||||
"-c",
|
||||
'model_reasoning_effort="low"',
|
||||
"--json",
|
||||
"--skip-git-repo-check",
|
||||
"-s",
|
||||
"read-only",
|
||||
"-",
|
||||
];
|
||||
const command = process.env.WEKSA_CODEX_EXECUTABLE ?? "C:\\Users\\Meta\\AppData\\Roaming\\npm\\codex.cmd";
|
||||
const run = await runCommand(command, args, {
|
||||
cwd: repoRoot,
|
||||
input: prompt,
|
||||
timeoutMs: Number(process.env.WEKSA_GOLF_TIMEOUT_MS ?? 240_000),
|
||||
});
|
||||
await writeFile(resolve(outputDir, `${sanitizeJob(job)}.stdout.jsonl`), run.stdout, "utf8");
|
||||
await writeFile(resolve(outputDir, `${sanitizeJob(job)}.stderr.txt`), run.stderr, "utf8");
|
||||
if (run.code !== 0) {
|
||||
throw new Error(`Codex generation failed for ${job}:\n${run.stderr || run.stdout}`);
|
||||
}
|
||||
const text = extractLastCodexAgentMessage(run.stdout).trim();
|
||||
if (!text) {
|
||||
throw new Error(`Codex generation produced no final text for ${job}.`);
|
||||
}
|
||||
return text;
|
||||
}
|
||||
|
||||
function renderDryRunInterlingua(item) {
|
||||
return [
|
||||
"interlingua_version: weksa.interlingua.v0",
|
||||
`packet_id: metame-casual-pre2025-${item.id}`,
|
||||
"kind: persona_discord_turn_intent",
|
||||
"provenance:",
|
||||
" produced_by: dry_run_fixture_from_existing_interlingua",
|
||||
"context:",
|
||||
" medium: Discord",
|
||||
" fixture_id: metame-casual-pre2025",
|
||||
` item_id: ${item.id}`,
|
||||
"discourse:",
|
||||
...indentBlock(item.interlinguaBlock, " "),
|
||||
"constraints:",
|
||||
" lowering:",
|
||||
" target_profile: weksa.target_cultural_ontology.en-US.metacrat_casual_pre2025.v0",
|
||||
" avoid_surface_copy: true",
|
||||
].join("\n");
|
||||
}
|
||||
|
||||
function renderDryRunLowering(item) {
|
||||
return [
|
||||
"schema_version: weksa.persona_culture_lowering_output.v0",
|
||||
"fixture_id: metame-casual-pre2025",
|
||||
`item_id: ${item.id}`,
|
||||
`spoken_text: ${JSON.stringify(item.groundTruth)}`,
|
||||
"trace:",
|
||||
" activated_profiles:",
|
||||
" - weksa.target_cultural_ontology.en-US.metacrat_casual_pre2025.v0",
|
||||
" activated_affordances:",
|
||||
" - dry_run_answer_key_oracle",
|
||||
" notes:",
|
||||
" - Dry run uses answer key only to verify harness plumbing. Use --real for model golf.",
|
||||
].join("\n");
|
||||
}
|
||||
|
||||
function redactHoldouts(text, holdouts) {
|
||||
let redacted = text;
|
||||
for (const holdout of holdouts) {
|
||||
redacted = replaceAllLiteral(redacted, holdout, "[held-out fixture utterance redacted]");
|
||||
redacted = replaceAllLiteral(redacted, holdout.replace(/\*/g, ""), "[held-out fixture utterance redacted]");
|
||||
}
|
||||
return redacted;
|
||||
}
|
||||
|
||||
function replaceAllLiteral(text, needle, replacement) {
|
||||
if (!needle) {
|
||||
return text;
|
||||
}
|
||||
return text.split(needle).join(replacement);
|
||||
}
|
||||
|
||||
function extractSpokenText(text) {
|
||||
const match = /^spoken_text:\s*(.+)$/m.exec(text);
|
||||
if (!match) {
|
||||
return text.trim().split(/\r?\n/).find((line) => line.trim().length > 0)?.trim() ?? "";
|
||||
}
|
||||
const value = match[1].trim();
|
||||
if (value.startsWith("\"")) {
|
||||
try {
|
||||
return JSON.parse(value);
|
||||
} catch {
|
||||
return value.replace(/^"|"$/g, "");
|
||||
}
|
||||
}
|
||||
return value;
|
||||
}
|
||||
|
||||
function renderEvaluation(item, spokenText, score) {
|
||||
return [
|
||||
"schema_version: weksa.persona_golf_item_evaluation.v0",
|
||||
`fixture_id: metame-casual-pre2025`,
|
||||
`item_id: ${item.id}`,
|
||||
`message_id: "${item.messageId}"`,
|
||||
`generated: ${JSON.stringify(spokenText)}`,
|
||||
`ground_truth: ${JSON.stringify(item.groundTruth)}`,
|
||||
"score:",
|
||||
` exact_normalized: ${score.exact}`,
|
||||
` token_precision: ${score.precision.toFixed(3)}`,
|
||||
` token_recall: ${score.recall.toFixed(3)}`,
|
||||
` token_f1: ${score.f1.toFixed(3)}`,
|
||||
].join("\n") + "\n";
|
||||
}
|
||||
|
||||
function scoreText(generated, truth) {
|
||||
const left = normalizeForScore(generated);
|
||||
const right = normalizeForScore(truth);
|
||||
const leftTokens = left.split(/\s+/).filter(Boolean);
|
||||
const rightTokens = right.split(/\s+/).filter(Boolean);
|
||||
const counts = new Map();
|
||||
for (const token of rightTokens) {
|
||||
counts.set(token, (counts.get(token) ?? 0) + 1);
|
||||
}
|
||||
let overlap = 0;
|
||||
for (const token of leftTokens) {
|
||||
const count = counts.get(token) ?? 0;
|
||||
if (count > 0) {
|
||||
overlap += 1;
|
||||
counts.set(token, count - 1);
|
||||
}
|
||||
}
|
||||
const precision = leftTokens.length ? overlap / leftTokens.length : 0;
|
||||
const recall = rightTokens.length ? overlap / rightTokens.length : 0;
|
||||
const f1 = precision + recall ? (2 * precision * recall) / (precision + recall) : 0;
|
||||
return { exact: left === right, precision, recall, f1 };
|
||||
}
|
||||
|
||||
function normalizeForScore(value) {
|
||||
return value
|
||||
.toLowerCase()
|
||||
.replace(/[*_`~.,!?;:'"()[\]{}]/g, "")
|
||||
.replace(/\s+/g, " ")
|
||||
.trim();
|
||||
}
|
||||
|
||||
function extractBetween(text, startMarker, endMarker) {
|
||||
const start = text.indexOf(startMarker);
|
||||
const end = text.indexOf(endMarker, start + startMarker.length);
|
||||
if (start < 0 || end < 0 || end <= start) {
|
||||
throw new Error(`Could not extract section ${startMarker}`);
|
||||
}
|
||||
return text.slice(start + startMarker.length, end);
|
||||
}
|
||||
|
||||
function runCommand(command, args, { cwd, input = "", timeoutMs = 120_000 }) {
|
||||
return new Promise((resolveRun) => {
|
||||
const isCmdShim = /\.cmd$/i.test(command) || /\.bat$/i.test(command);
|
||||
const spawnCommand = isCmdShim ? (process.env.ComSpec ?? "cmd.exe") : command;
|
||||
const spawnArgs = isCmdShim ? ["/d", "/s", "/c", command, ...args] : args;
|
||||
const child = spawn(spawnCommand, spawnArgs, {
|
||||
cwd,
|
||||
env: process.env,
|
||||
stdio: ["pipe", "pipe", "pipe"],
|
||||
windowsHide: true,
|
||||
});
|
||||
let stdout = "";
|
||||
let stderr = "";
|
||||
const timer = setTimeout(() => child.kill(), timeoutMs);
|
||||
child.stdout.setEncoding("utf8");
|
||||
child.stderr.setEncoding("utf8");
|
||||
child.stdout.on("data", (chunk) => { stdout += chunk; });
|
||||
child.stderr.on("data", (chunk) => { stderr += chunk; });
|
||||
child.on("error", (error) => {
|
||||
clearTimeout(timer);
|
||||
resolveRun({ code: -1, stdout, stderr: `${stderr}\n${error.message}` });
|
||||
});
|
||||
child.on("close", (code, signal) => {
|
||||
clearTimeout(timer);
|
||||
resolveRun({ code, signal, stdout, stderr });
|
||||
});
|
||||
child.stdin.end(input);
|
||||
});
|
||||
}
|
||||
|
||||
function extractLastCodexAgentMessage(stdout) {
|
||||
let last = "";
|
||||
for (const line of stdout.split(/\r?\n/)) {
|
||||
if (!line.trim()) {
|
||||
continue;
|
||||
}
|
||||
try {
|
||||
const event = JSON.parse(line);
|
||||
const message = event?.msg?.message ?? event?.message ?? event?.text;
|
||||
if (typeof message === "string" && message.trim()) {
|
||||
last = message;
|
||||
}
|
||||
const itemText = event?.item?.text;
|
||||
if (typeof itemText === "string" && itemText.trim()) {
|
||||
last = itemText;
|
||||
}
|
||||
const content = event?.item?.content;
|
||||
if (Array.isArray(content)) {
|
||||
const text = content
|
||||
.map((part) => typeof part?.text === "string" ? part.text : "")
|
||||
.join("\n")
|
||||
.trim();
|
||||
if (text) {
|
||||
last = text;
|
||||
}
|
||||
}
|
||||
} catch {
|
||||
if (line.trim()) {
|
||||
last = line.trim();
|
||||
}
|
||||
}
|
||||
}
|
||||
return last;
|
||||
}
|
||||
|
||||
function indentBlock(block, prefix) {
|
||||
return block.split(/\r?\n/).map((line) => `${prefix}${line}`).join("\n").split(/\r?\n/);
|
||||
}
|
||||
|
||||
function readArg(name) {
|
||||
const index = process.argv.indexOf(name);
|
||||
if (index < 0) {
|
||||
return undefined;
|
||||
}
|
||||
return process.argv[index + 1];
|
||||
}
|
||||
|
||||
function escapeRegExp(value) {
|
||||
return value.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
|
||||
}
|
||||
|
||||
function sanitizeJob(value) {
|
||||
return value.replace(/[^A-Za-z0-9_.-]+/g, "_");
|
||||
}
|
||||
Loading…
Reference in a new issue