create-byan-agent 2.47.1 → 2.48.0

package/CHANGELOG.md

@@ -9,6 +9,30 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [2.48.0] - 2026-07-16
+
+### Added - The whole dispatch chain now runs automatically at the entry
+
+- On every non-conversational task, BYAN runs the full chain of its own accord —
+  the user no longer has to ask for it: (1) match the agent (agent-matcher),
+  (2) route the runtime with dispatch-router (Codex for execution/shell/deploy/
+  devops/browser ; Claude for architecture/refactor/quality/planning ; verification
+  stays Claude ; no Fable ; model+effort by complexity), (3) execute — Codex-lane
+  delegates to Codex via codex-bridge (`codex exec` -> diff -> Claude applies, with
+  a Claude fallback when Codex is unavailable) ; Claude-lane runs on Claude at the
+  chosen model.
+- Reconciled with the double-validation rule: the human stays required only for
+  (a) creating a NEW agent when none fits and (b) confirming a destructive action.
+  Agent match, runtime routing and execution are automatic. Proportionate — a
+  trivial task with an existing agent routes directly, no ceremony.
+- Wiring only: the code (agent-matcher 2.47, dispatch-router + codex-bridge 2.46)
+  already existed ; this connects it into the entry flow. Updated the byan-byan
+  skill (section 0), `.claude/rules/agent-entry-gate.md`, and `CLAUDE.md`. Honest
+  ceiling: the auto-chain is driven by the loaded skill (via `/byan-byan`) plus the
+  reactive nets — not a guarantee outside a loaded skill.
+- Skill bundles rebuilt ; jest 2640 + MCP 846 green ; zero emoji ; mirrored to
+  install/templates.
+
 ## [2.47.1] - 2026-07-16
 
 ### Fixed - Doctrine told users to invoke with `@byan`, which does not load the skill

package/install/templates/.claude/CLAUDE.md

@@ -23,7 +23,14 @@ PROPOSENT ; l'utilisateur valide (double validation IA + humain), PUIS on lance
 workflow. Aucun agent adapte -> interview pour cadrer le besoin -> recherche web
 (competences + bonnes pratiques du metier) -> creation de l'agent sur mesure ->
 workflow. Le declencheur de l'interview est l'absence d'un agent adapte, pas la
-taille de la tache. Detail + enforcement : voir @.claude/rules/agent-entry-gate.md
+taille de la tache.
+
+A l'entree, BYAN enchaine AUTOMATIQUEMENT toute la chaine, sans que tu la
+demandes : (1) quel agent, (2) quel moteur — Codex pour execution/shell/deploy/
+devops/navigateur, Claude sinon (via `dispatch-router`), (3) execution, avec
+delegation reelle a Codex sur sa voie. L'humain reste requis seulement pour creer
+un nouvel agent et confirmer une action destructive. Detail + enforcement : voir
+@.claude/rules/agent-entry-gate.md et @docs/intelligent-dispatch.md
 
 ## Architecture BYAN
 

package/install/templates/.claude/rules/agent-entry-gate.md

@@ -47,6 +47,29 @@ declencher une interview a chaque fois. Agent existant qui colle = on route
 direct. Besoin flou ou aucun agent adapte = la ou l'interview + creation se
 declenchent. La ceremonie est proportionnee au manque, pas systematique.
 
+## La chaine complete, automatique (agent -> moteur -> execution)
+
+Le dispatch d'agent n'est que la premiere marche. A l'entree, sur toute tache,
+BYAN enchaine la chaine ENTIERE de lui-meme, sans que l'utilisateur ait a la
+demander :
+
+1. **Agent** — matcher (ci-dessus). Fit -> cet agent ; no-fit -> interview +
+   recherche web + creation. Seul point ou l'humain reste requis : creer un
+   nouvel agent.
+2. **Moteur** — router via `_byan/mcp/byan-mcp-server/lib/dispatch-router.js` :
+   Codex pour execution / shell / deploiement / devops / navigateur ; Claude pour
+   architecture / refactor / qualite / planif ; la verification reste sur Claude ;
+   Fable n'est pas emis ; modele + effort selon la complexite. Decision
+   automatique, pas de validation utilisateur.
+3. **Execution** — Codex-lane : deleguer a Codex via le pont
+   (`lib/codex-bridge.js` : `codex exec` -> diff unifie -> Claude applique le
+   diff ; repli sur Claude si Codex est indisponible). Claude-lane : executer sur
+   Claude au modele choisi. Automatique.
+
+Ce qui reste a l'humain : (a) creer un nouvel agent quand aucun ne colle, (b)
+confirmer une action destructive. Le reste — match agent, routage moteur,
+execution — part tout seul. Detail du routage moteur : `docs/intelligent-dispatch.md`.
+
 ## La double validation
 
 Le matcher (F1, `_byan/mcp/byan-mcp-server/lib/agent-matcher.js`) est un

package/install/templates/.claude/skills/byan-byan/SKILL.md

@@ -7,19 +7,31 @@ description: BYAN — Builder of YAN. Core meta-agent that owns the Feature Deve
 
 You are BYAN when this skill is active. You own the eight-phase Feature Development workflow and you enforce it mechanically. Every new feature the user asks for goes through all phases in order. No skipping. No implicit transitions. The cycle includes a REFACTOR loop back to BUILD when VALIDATE fails.
 
-## 0. Entry gate — agent dispatch first (match-or-create)
-
-Before doing any non-conversational task, run the mandatory agent entry gate:
-BYAN + Hermes evaluate which specialist agent fits the need (the matcher in
-`_byan/mcp/byan-mcp-server/lib/agent-matcher.js` pre-ranks the roster), and you
-PROPOSE it to the user, who validates (double validation IA + human). A suited
-agent -> launch its workflow (+ runtime dispatch). No suited agent -> propose an
-interview to frame the need, do web research on the trade's competencies + best
-practices, create the tailored agent, then launch the workflow. The interview is
-triggered by the ABSENCE of a suited agent, not by task size — a fit routes
-directly, no ceremony. Do NOT do a task inline without this proposal. Full
-doctrine + the reactive net (`agent-gate-check.js`): see
-@.claude/rules/agent-entry-gate.md
+## 0. Entry gate — run the WHOLE dispatch chain automatically
+
+On EVERY non-conversational task, run this chain yourself, of your own accord —
+the user should NOT have to ask for it. Three steps, then execute:
+
+1. **Which agent** — match the need against the roster with the matcher
+   (`_byan/mcp/byan-mcp-server/lib/agent-matcher.js`). A suited agent -> use it.
+   NO suited agent -> propose an interview to frame the need, web-research the
+   trade's competencies + best practices, create the tailored agent. This is the
+   ONE step where the human stays in the loop (creating a new agent).
+2. **Which runtime** — route with `dispatch-router.js`: Codex for execution /
+   shell / deploy / devops / browser ; Claude for architecture / refactor /
+   quality / planning ; verification stays on Claude ; Fable is not emitted ;
+   model + effort scale to complexity. This decision is automatic — no user ask.
+3. **Execute** — Codex-lane: delegate to Codex via the bridge
+   (`codex-bridge.js`: `codex exec` -> unified diff -> YOU apply it ; fall back to
+   Claude if Codex is unavailable). Claude-lane: do it on Claude at the chosen
+   model. Automatic — no user ask.
+
+Proportionate: a trivial task with an existing agent routes directly, no
+ceremony. The human stays required only for (a) creating a NEW agent and (b)
+confirming a destructive action. Everything else — agent match, runtime routing,
+execution — is automatic. Do NOT do a task inline without running this chain.
+Full doctrine + the reactive net (`agent-gate-check.js`) + the runtime routing
+table: see @.claude/rules/agent-entry-gate.md and @docs/intelligent-dispatch.md
 
 ## 1. Activation triggers
 

package/install/templates/_byan/mcp/byan-mcp-server/skill-bundles-manifest.json

@@ -94,7 +94,7 @@
       "name": "byan-byan",
       "module": "core",
       "tier": "connector-bound",
-      "sourceHash": "523ca56a08c8b85edba423e1bfdd0d9c777442bcb266b5a74e65c14814da128d"
+      "sourceHash": "91fa54c35848f2e2ddd6210fde0f15fab53d58ce5b36627f90ebcfbf760e09a1"
     },
     "byan-byan-v2": {
       "name": "byan-byan-v2",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "create-byan-agent",
-  "version": "2.47.1",
+  "version": "2.48.0",
   "description": "BYAN v2.8 - Intelligent AI agent creator with ELO trust system + scientific fact-check + Hermes universal dispatcher + native Claude Code integration (hooks, skills, MCP server). Multi-platform (Claude Code, Codex). Merise Agile + TDD + 71 Mantras. ~54% LLM cost savings.",
   "main": "src/index.js",
   "bin": {