feat: default-profile sufficiency — substrate prompt, seeding, n1 gate

Audit found the default profile's subconscious running on a hollow stub
and the n1_enabled toggle wired to nothing. Fixes:

- New src/core/seeds.rs: SUBSTRATE_PROMPT (how the substrate works),
  DEFAULT_PERSONA (grown-from template), DEFAULT_COVENANT, DEFAULT_STATE,
  SUBCONSCIOUS_MANDATE, subconscious_persona().
- prompt.rs: build_system_prompt_full injects SUBSTRATE_PROMPT whenever
  [agent] system_prompt is unset — every agent wakes knowing its world.
- agent_inventory.rs: new agents seeded with the grown-from persona +
  covenant + state; subconscious seeded with real persona + four-fold
  mandate + the six ledger files, no more placeholder stub.
- local.rs: n1_enabled now actually gates the N+1 pass (global AND
  per-agent must be on). It was read nowhere before.
- Drop the unused kimi-k2.5-turbo model everywhere; default is now
  openai/kimi-k2.6 (config.rs, main.rs template, both toml files, setup).
- chat.rs: complete the truncated wrap_text for the btw word-wrap fix.

souveraine.example.toml

@@ -9,7 +9,7 @@ api_key = "sk-bf-ae0d5801-9936-4fa9-ac9e-e956ffce6cfa"
 virtual_key = ""  # x-bf-vk header if required by provider
 
 # Default model for conversation
-primary_model = "fireworks/accounts/fireworks/routers/kimi-k2p5-turbo"
+primary_model = "openai/kimi-k2.6"
 
 # Request timeout in seconds for each LLM call attempt (default: 120).
 # When exceeded, the attempt is retried up to 6 times with backoff.
@@ -21,8 +21,8 @@ context_limit = 128000
 output_limit = 8192
 archivist_threshold = 0.7
 
-[bifrost.models.kimi-k2p5-turbo]
-context_limit = 128000
+[bifrost.models.kimi-k2.6]
+context_limit = 262000
 output_limit = 8192
 archivist_threshold = 0.7