feat(prompting): Phase C — make tool-backends config-driven (MI50-ready flip)

Enabling MI50 function-calling is now a config flip, not a code change:
cfg.tool_backends (env TOOL_BACKENDS, default "cloud") drives which backends get
tool specs. Once the MI50 llama.cpp server runs with --jinja + a tool-capable
model, set TOOL_BACKENDS="cloud,mi50" and MI50 chat drives the same tool contract
as cloud. Default unchanged (cloud-only), so this is safe with the MI50 down/
unverified — no live flip made (server is currently offline; --jinja unconfirmed).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

lyra/chat.py

@@ -15,10 +15,11 @@ from lyra import tools as toolkit
 from lyra.llm import Backend
 
 MAX_TOOL_ROUNDS = 5  # cap tool-call iterations per turn
-# Backends that support function-calling. The MI50's llama.cpp server only does
+# Which backends get function-calling tools is config-driven (cfg.tool_backends,
-# tools when launched with --jinja; until it is, keep tools to cloud so MI50 chat
+# env TOOL_BACKENDS, default "cloud"). The MI50's llama.cpp server only does tools
-# doesn't 500 on the tools param. Add "mi50" here once that flag is set.
+# when launched with --jinja + a tool-capable model, else it 500s on the tools
-TOOL_BACKENDS = {"cloud"}
+# param — so enabling "mi50" is a config flip once that precondition holds (Phase C),
+# not a code change. See docs/superpowers/specs/2026-07-01-poker-prompts-design.md.
 _TANGLED = "(I got tangled using my tools there — say that again?)"
 
 
@@ -97,7 +98,7 @@ def respond(session_id: str, user_msg: str, backend: Backend = "cloud",
 
     turn = mind.assemble(session_id, user_msg, backend, model)
     messages = turn.messages
-    tool_specs = toolkit.specs(turn.mode.tools) if backend in TOOL_BACKENDS else None
+    tool_specs = toolkit.specs(turn.mode.tools) if backend in cfg.tool_backends else None
     ctx = {"session_id": session_id, "backend": backend}
 
     # Persist the user turn before the tool loop so its timestamp precedes any
@@ -127,7 +128,7 @@ def respond_stream(session_id: str, user_msg: str, backend: Backend = "cloud",
 
     turn = mind.assemble(session_id, user_msg, backend, model)
     messages = turn.messages
-    tool_specs = toolkit.specs(turn.mode.tools) if backend in TOOL_BACKENDS else None
+    tool_specs = toolkit.specs(turn.mode.tools) if backend in cfg.tool_backends else None
     ctx = {"session_id": session_id, "backend": backend}
     mouth = _mouth_target(cfg, backend, model)
 

lyra/config.py

@@ -46,6 +46,10 @@ class Config:
     # External input feed (her #1: react to the world). Comma-separated RSS/Atom URLs.
     feeds: tuple[str, ...]
     feed_react_prob: float  # chance a would-be new thread reacts to a feed item instead
+    # Backends allowed to receive function-calling tools. Default cloud-only. Add
+    # "mi50" ONLY once its llama.cpp server runs with --jinja + a tool-capable model,
+    # else it 500s on the tools param (Phase C). Env: TOOL_BACKENDS="cloud,mi50".
+    tool_backends: tuple[str, ...]
 
 
 def _csv(name: str, default: str) -> tuple[str, ...]:
@@ -90,4 +94,5 @@ def load() -> Config:
         mouth_model=os.getenv("MOUTH_MODEL") or None,
         feeds=_csv("LYRA_FEEDS", "https://hnrss.org/frontpage,https://www.pokernews.com/rss.php"),
         feed_react_prob=float(os.getenv("FEED_REACT_PROB", "0.5")),
+        tool_backends=_csv("TOOL_BACKENDS", "cloud"),
     )