kibi-opencode 2.0.0 → 2.0.2

package/README.md

@@ -52,7 +52,7 @@ The plugin now uses a posture-aware, low-token smart-enforcement model before em
 
 - **Repo posture detection**: distinguishes `root_active`, `root_partial`, `root_uninitialized`, `vendored_only`, and `hybrid_root_plus_vendored`
 - **Risk classification**: separates `safe_docs_only`, `safe_test_only`, `kb_doc_structural`, `req_policy_candidate`, `behavior_candidate`, `traceability_candidate`, and `manual_kb_edit`
-- **Source-linked Kibi links**: risky code edits (`behavior_candidate`, `traceability_candidate`) prepend a concise list of existing Kibi links (e.g., `- Existing Kibi links: REQ-001, REQ-002`) when 1-3 concrete source-linked KB hits are found in `.kb/symbols.yaml`. Skip on cache hit.
+- **Source-linked Kibi links**: risky code edits (`behavior_candidate`, `traceability_candidate`) prepend a concise list of existing Kibi links (e.g., `- Existing Kibi links: REQ-cli-gc, REQ-cli-check`) when 1-3 concrete source-linked KB hits are found in `.kb/symbols.yaml`. Skip on cache hit.
 - **Start-task risky cue**: authoritative risky edits also add a compact Kibi context cue so agents can start with explicit source-linked guidance before acting, while staying inside the same single prompt block and token budget.
 - **Effective mode gating**: `advisory` (default) never blocks; `strict` escalates checks and reminders for `root_active` and `hybrid_root_plus_vendored` postures when `requireRootKbForStrict` is enabled; `hard` fails closed for authoritative roots and linked git worktrees, injecting capability-based recovery steps until the Kibi checkpoint passes. `maintenanceDegraded` overrides everything back to `advisory`.
 - **Low-token prompt policy**: docs-only and test-only edits avoid unnecessary discovery prompts; vendored-only repos suppress operational bootstrap nudges; at most one contextual block is injected per prompt (≤120 words, ≤5 bullets)
@@ -303,7 +303,7 @@ Disable specific features while keeping others:
 
 ## Troubleshooting
 
-If you see a false "workspace needs Kibi bootstrap" warning even though `.kb/manifest.json` and the canonical knowledge lanes exist, this usually means a stale plugin cache. Leftover `.kb/config.json` custom paths are ignored. See [the main troubleshooting docs](../../docs/troubleshooting.md#opencode-shows-workspace-needs-kibi-bootstrap-before-the-tui) for recovery steps.
+If you see a false "workspace needs Kibi bootstrap" warning even though `.kb/manifest.json` and the canonical knowledge lanes exist, this usually means a stale plugin cache. Leftover `.kb/config.json` custom paths are ignored. See [the troubleshooting guide](https://looted.github.io/kibi/guide/troubleshooting.html#opencode-shows-workspace-needs-kibi-bootstrap-before-the-tui) for recovery steps.
 
 ## Architecture
 

package/dist/prompt.js

@@ -433,7 +433,7 @@ This keeps domain truths centralized, searchable, and contradiction-safe.`;
 Your recent code edit contains a comment that looks like a **technical decision** (tradeoffs, rationale, or architecture choices).
 
 **Action**: Instead of inline comments, route this to an ADR entity:
-- Create \`.kb/adr/ADR-xxx.md\` documenting the decision
+- Create \`.kb/adr/ADR-<decision>.md\` documenting the decision
 - Include context, options considered, and the chosen approach
 - Link to constrained code symbols
 
@@ -444,7 +444,7 @@ This preserves decision context for future maintainers.`;
 Your recent code edit contains a comment that looks like **behavior intent** (system capabilities or user-facing requirements).
 
 **Action**: Instead of inline comments, route this to a REQ entity:
-- Create \`.kb/requirements/REQ-xxx.md\` with the behavior description
+- Create \`.kb/requirements/REQ-<area>-<behavior>.md\` (named by the behavior, never the next number) with the behavior description
 - Add SCEN and TEST entities for specification and verification
 - Link code: production uses \`implements\` (symbol→req) for ownership; test code uses \`executable_for\`; \`covered_by\` is coverage evidence only
 

package/dist/risk-classifier.js

@@ -82,7 +82,7 @@ export function classifyRisk(params) {
             if (hasDurableComment || !hasTraceability) {
                 const reasons = [];
                 if (!hasTraceability) {
-                    reasons.push("Code file contains exports without // implements REQ-xxx annotation");
+                    reasons.push("Code file contains exports without // implements REQ-<area>-<behavior> annotation");
                 }
                 if (hasDurableComment) {
                     reasons.push("Durable knowledge comment detected — traceability review recommended");

package/dist/tui.js

@@ -6,6 +6,6 @@ var tui_default = {
   tui
 };
 export {
-  tui,
-  tui_default as default
+  tui_default as default,
+  tui
 };

package/dist/version-metadata.json

@@ -1 +1 @@
-{"opencode":"2.0.0","mcp":"2.0.0","cli":"2.0.0","core":"0.12.0"}
+{"opencode":"2.0.2","mcp":"2.2.0","cli":"2.2.0","core":"0.14.0"}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "kibi-opencode",
-  "version": "2.0.0",
+  "version": "2.0.2",
   "description": "Kibi OpenCode plugin - thin adapter to integrate Kibi with OpenCode sessions",
   "type": "module",
   "main": "dist/index.js",
@@ -37,9 +37,7 @@
       "default": "./dist/tui.js"
     }
   },
-  "files": [
-    "dist"
-  ],
+  "files": ["dist"],
   "engines": {
     "node": ">=22"
   },
@@ -62,7 +60,7 @@
     "@opencode-ai/plugin": "^1.4.7",
     "@opentui/core": "^0.1.99",
     "@opentui/solid": "^0.1.99",
-    "kibi-runtime": "^2.0.0"
+    "kibi-runtime": "^2.0.2"
   },
   "devDependencies": {
     "@types/node": "latest",