wizz-method 2.25.0 → 2.25.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json
CHANGED
|
@@ -20,6 +20,11 @@ activation_steps_prepend = []
|
|
|
20
20
|
|
|
21
21
|
activation_steps_append = []
|
|
22
22
|
|
|
23
|
+
# Cheap dispatch rule (single source in the wizz module's _shared/). Lives here
|
|
24
|
+
# too because the router can hand a code request straight to this workflow,
|
|
25
|
+
# skipping the area persona that normally carries it.
|
|
26
|
+
include = ["../../_shared/despacho-barato.md"]
|
|
27
|
+
|
|
23
28
|
# Persistent facts the workflow keeps in mind for the whole run
|
|
24
29
|
# (standards, compliance constraints, stylistic guardrails).
|
|
25
30
|
# Distinct from the runtime memory sidecar — these are static context
|
|
@@ -20,6 +20,11 @@ activation_steps_prepend = []
|
|
|
20
20
|
|
|
21
21
|
activation_steps_append = []
|
|
22
22
|
|
|
23
|
+
# Cheap dispatch rule (single source in the wizz module's _shared/). Lives here
|
|
24
|
+
# too because the router hands one-off code requests straight to this workflow,
|
|
25
|
+
# skipping the area persona that normally carries it.
|
|
26
|
+
include = ["../../_shared/despacho-barato.md"]
|
|
27
|
+
|
|
23
28
|
# Persistent facts the workflow keeps in mind for the whole run
|
|
24
29
|
# (standards, compliance constraints, stylistic guardrails).
|
|
25
30
|
# Distinct from the runtime memory sidecar — these are static context
|
|
@@ -6,4 +6,4 @@
|
|
|
6
6
|
# once. Don't copy this text into another toml: reference it via `include`.
|
|
7
7
|
# ---
|
|
8
8
|
|
|
9
|
-
Mechanical work (scanning, lookup, repetitive diff, an already-specified change): don't run it in the session when it's large; dispatch wizz-exec-mechanical/wizz-exec-standard subagents, partitioned one per file/module, up to 4 concurrent. The session's model is the boss: it does common work itself, dispatches, and decides with the user. Hard work escalates to wizz-exec-strong when the session's own tier isn't enough (same error twice, cause unclear, or architecture/schema/auth/payments/3+ modules); strong never dispatches, it returns ESCALAR to the session, which then dispatches wizz-exec-ultra with strong's findings. Before any dispatch, measure the size, not just the difficulty: more than one layer (database, backend/worker, app/UI, external automation) or ~8 files means one executor per layer, each brief with max_calls at about 2/3 of the tier's turn cap; a cross-layer story never goes whole to one executor, and a partial return gets split, not "continue". Diff review always goes to wizz-exec-review (pinned to the Strong tier, never inherits the session). Tell the user the tier and quantity of each dispatch. Full ladder in `_shared/model-ladder.md` and the rule in `_shared/token-economy.md` of the wizz module.
|
|
9
|
+
Mechanical work (scanning, lookup, repetitive diff, an already-specified change): don't run it in the session when it's large (more than 3 files, or a scan across a directory; a tiny mechanical change stays in the session); dispatch wizz-exec-mechanical/wizz-exec-standard subagents, partitioned one per file/module, up to 4 concurrent. The session's model is the boss: it does common work itself, dispatches, and decides with the user. Hard work escalates to wizz-exec-strong when the session's own tier isn't enough (same error twice, cause unclear, or architecture/schema/auth/payments/3+ modules); strong never dispatches, it returns ESCALAR to the session, which then dispatches wizz-exec-ultra with strong's findings. Before any dispatch, measure the size, not just the difficulty: more than one layer (database, backend/worker, app/UI, external automation) or ~8 files means one executor per layer, each brief with max_calls at about 2/3 of the tier's turn cap; a cross-layer story never goes whole to one executor, and a partial return gets split, not "continue". Diff review always goes to wizz-exec-review (pinned to the Strong tier, never inherits the session). Tell the user the tier and quantity of each dispatch. Full ladder in `_shared/model-ladder.md` and the rule in `_shared/token-economy.md` of the wizz module.
|