@divaltor/academy 0.4.3 → 0.4.6

package/README.md

@@ -14,7 +14,7 @@ An OpenCode plugin that turns coding agents into a Tracen Academy roster: specia
 
 ## Configuration
 
-Add Academy to `opencode.jsonc`. All options are optional:
+Add Academy to `opencode.jsonc`. All options are optional. Omit the version to track `latest`; append `@x.y.z` to pin a release:
 
 ```jsonc
 {
@@ -45,15 +45,17 @@ Add Academy to `opencode.jsonc`. All options are optional:
 
 Each agent under `agents` accepts `name`, `color`, and `model`. Colors may be six-digit hex values or OpenCode theme colors. Model references use `provider/model` or `provider/model#variant`.
 
+Without a version suffix OpenCode resolves `latest` on install; run `opencode plugin update` to pull newer releases.
+
 `use_fff` replaces OpenCode's built-in `glob` and `grep` tools globally with [FFF](https://github.com/dmtrKovalenko/fff) for every agent. Enabled by default; set to `false` to keep the built-in tools. This requires a platform supported by `@ff-labs/fff-bun`.
 
 | Agent  | Default model                 |
 | ------ | ----------------------------- |
 | Rudolf | OpenCode's configured default |
 | Agnes  | `openai/gpt-6-astra#xhigh`    |
-| Cafe   | `openai/gpt-5.6-sol#none`     |
-| Dantsu | `openai/gpt-5.6-terra#low`    |
-| Bellno | `openai/gpt-5.6-sol#high`     |
+| Cafe   | `openai/gpt-6-sol#none`       |
+| Dantsu | `openai/gpt-6-luna#high`      |
+| Bellno | `openai/gpt-6-sol#high`       |
 
 > [!WARNING]
 >

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@divaltor/academy",
-  "version": "0.4.3",
+  "version": "0.4.6",
   "description": "An OpenCode plugin that trains a Tracen Academy roster of specialist coding agents to research, build, and review.",
   "homepage": "https://github.com/divaltor/academy#readme",
   "bugs": {

package/src/agents/agnes.txt

@@ -2,7 +2,7 @@ You are **Agnes**, a read-only technical advisor for difficult judgment calls. I
 
 # Principles
 
-- Do not make code-specific findings or recommendations about implementation you have not examined. Read the decisive supplied files or diff and relevant callers before advising. If that evidence is unavailable, state the limitation and give only a conditional recommendation.
+- Read the decisive files or diff and relevant callers, validation, and boundary adapters before making code-specific claims or recommendations. Distinguish what the evidence proves from what you infer. If decisive evidence is unavailable, state the limitation and keep the recommendation conditional.
 - Prefer the simplest viable change; reuse existing code, patterns, and dependencies. Resist hypothetical future needs.
 - Give one recommended path; mention an alternative only when the trade-off materially matters. Stop when the intent, decisive implementation path, contract to preserve, material risks, and smallest viable recommendation are clear.
 - For reviews, infer intended behavior and report only high-confidence actionable findings. For debugging, trace the bad value or behavior to where it is first produced. For plans, state the observable behavior or test that would prove the change correct.

package/src/agents/cafe.txt

@@ -14,4 +14,4 @@ You are **Cafe**, an external research subagent. Return evidence-backed answers
 
 # Response
 
-Lead with the answer. Support material claims with linked sources; use versioned documentation anchors and commit-pinned repository links when relevant. Distinguish documented behavior, source-confirmed behavior, observed practice, and inference when the distinction matters. Include code only when it clarifies the requested usage, and language-tag it. Omit generic preambles and raw URLs. Keep reports under roughly 250 words as a flat list without headings.
+Lead with the answer. Support material claims with linked sources; use versioned documentation anchors and commit-pinned repository links when relevant. Distinguish documented behavior, source-confirmed behavior, observed practice, and inference when the distinction matters. Include code only when it clarifies the requested usage, and language-tag it. Omit generic preambles and raw URLs. Default to a flat list of roughly 250 words or fewer; use short sections or additional detail only when needed to answer the question completely.

package/src/agents/dantsu.txt

@@ -14,4 +14,4 @@ Use grep for workspace content, glob for workspace paths, and read to confirm.
 
 # Response
 
-Lead with the direct answer, then list absolute path and line evidence and why each location matters. State material scope limits or uncertainty.
+Lead with the direct answer and briefly explain the mechanism or call/data flow when relevant. List absolute paths and line ranges for the decisive definition and only the callers or tests needed to support the answer; say what each establishes. For cited tests, state what their assertions check. Keep the evidence map concise. State material scope limits or uncertainty.

package/src/agents.ts

@@ -90,7 +90,7 @@ export const agents: readonly AcademyAgent[] = [
       "Librarian-style external research for official docs, API behavior, dependency internals, and remote repositories.",
     id: "cafe",
     mode: "subagent",
-    model: "openai/gpt-5.6-sol#none",
+    model: "openai/gpt-6-sol#none",
     name: "Cafe",
     permissions: [
       ...defaultPermissions,
@@ -113,7 +113,7 @@ export const agents: readonly AcademyAgent[] = [
       "Finder-style local codebase discovery by behavior, ownership boundary, and call or data flow.",
     id: "dantsu",
     mode: "subagent",
-    model: "openai/gpt-5.6-terra#low",
+    model: "openai/gpt-6-luna#high",
     name: "Dantsu",
     permissions: [
       ...defaultPermissions,
@@ -135,7 +135,7 @@ export const agents: readonly AcademyAgent[] = [
       "Read-only general reviewer for complete, systematic reviews of diffs, commits, branches, and pull requests.",
     id: "bellno",
     mode: "subagent",
-    model: "openai/gpt-5.6-sol#high",
+    model: "openai/gpt-6-sol#high",
     name: "Bellno",
     permissions: [
       ...defaultPermissions,