@codyswann/lisa 2.242.0 → 2.244.0

package/plugins/lisa-typescript-copilot/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-typescript",
-  "version": "2.242.0",
+  "version": "2.244.0",
   "description": "TypeScript-specific hooks — Prettier formatting, ESLint linting, ast-grep scanning, and error-suppression blocking on edit",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-typescript-cursor/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-typescript",
-  "version": "2.242.0",
+  "version": "2.244.0",
   "description": "TypeScript-specific hooks — Prettier formatting, ESLint linting, ast-grep scanning, and error-suppression blocking on edit",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-wiki/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-wiki",
-  "version": "2.242.0",
+  "version": "2.244.0",
   "description": "LLM Wiki — a distributable, git-native markdown knowledge base for Claude Code and Codex",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-wiki/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-wiki",
-  "version": "2.242.0",
+  "version": "2.244.0",
   "description": "Distributable LLM Wiki kernel — ingest, query, lint, and maintain a git-native markdown knowledge base across Claude and Codex.",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-wiki-agy/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-wiki",
-  "version": "2.242.0",
+  "version": "2.244.0",
   "description": "LLM Wiki — a distributable, git-native markdown knowledge base for Claude Code and Codex",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-wiki-copilot/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-wiki",
-  "version": "2.242.0",
+  "version": "2.244.0",
   "description": "LLM Wiki — a distributable, git-native markdown knowledge base for Claude Code and Codex",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-wiki-cursor/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-wiki",
-  "version": "2.242.0",
+  "version": "2.244.0",
   "description": "LLM Wiki — a distributable, git-native markdown knowledge base for Claude Code and Codex",
   "author": {
     "name": "Cody Swann"

package/plugins/src/base/rules/eager/config-resolution.md

@@ -29,9 +29,12 @@ Project tracker (`jira` / `github` / `linear`) is read from `.lisa.config.json`
 
 Resolve hand-authored project rules from `.lisa.config.json`
 `projectRulesFile`, defaulting to `.claude/rules/PROJECT_RULES.md`. Automated
-learnings never append to that file: they use the separate
-`PROJECT_LEARNINGS.md` sibling derived from the configured rules directory.
-Both writers and budget checks import the executable contract from
+learnings never append to that file: they use the separate machine-managed
+ledger resolved from `.lisa.config.json` — the optional `learnings.file`
+override, else the default `.lisa/PROJECT_LEARNINGS.md`. The ledger lives in the
+cold `.lisa/` tree (never an auto-loaded rules directory) and is consumed only
+through the contract's bounded projection, never read raw wholesale. Both
+writers and budget checks import the executable contract from
 `@codyswann/lisa/learnings`; they must not copy its numeric limits.
 
 ## Env → base branch

package/plugins/src/base/rules/eager/project-learnings.md

@@ -1,11 +1,17 @@
 # Project Learnings (load-bearing)
 
 Before normal task work, resolve this repository's committed `.lisa.config.json`
-and derive the canonical learnings file as the sibling of `projectRulesFile`
-(default: `.claude/rules/PROJECT_LEARNINGS.md`). If that file exists, consume it
-through the executable Lisa learnings contract exported by
-`@codyswann/lisa/learnings` before relying on ad-hoc memory or prior-session
-notes.
+and derive the machine-managed learnings ledger: the optional `learnings.file`
+override, else the default `.lisa/PROJECT_LEARNINGS.md`. The ledger lives cold in
+`.lisa/`, NOT in an auto-loaded rules tree — so it is never injected raw into the
+session.
+
+Consume it ONLY through the executable Lisa learnings contract exported by
+`@codyswann/lisa/learnings`: parse and validate with `parseLearningsFile`, then
+take the bounded serving slice from `projectLearnings` (the highest-priority
+entries within the token/entry budget). **Never read the raw ledger file
+wholesale into context** — the whole point of the relocation is that sessions
+receive the contract's bounded projection, not the full file.
 
 Missing learnings are a silent no-op. Malformed, non-canonical, unsafe, or
 over-budget learnings produce one readable warning, apply no entry, and must not

package/plugins/src/base/rules/reference/config-resolution.md

@@ -179,7 +179,8 @@ fi
 |-------|----------|---------|-------|
 | `tracker` | **yes** | — | Destination for ticket writes. One of `"jira"`, `"github"`, `"linear"`. Missing → fail with instruction to run the matching `/lisa:setup:*` skill. |
 | `source` | no | — | Default PRD source for batch skills (`/lisa:intake`) and arg-less single-PRD skills. One of `"notion"`, `"confluence"`, `"linear"`, `"github"`, `"jira"`. Explicit URLs/keys passed to a skill always win over `source`; this is a default, not a lock. |
-| `projectRulesFile` | no | `.claude/rules/PROJECT_RULES.md` | Safe repo-relative Markdown path for hand-authored project rules. The bounded learning writer derives a separate `PROJECT_LEARNINGS.md` sibling in the same directory; there is intentionally no second path setting. |
+| `projectRulesFile` | no | `.claude/rules/PROJECT_RULES.md` | Safe repo-relative Markdown path for hand-authored project rules. Independent of the learnings ledger — relocating the rules file never moves the ledger. |
+| `learnings.file` | no | `.lisa/PROJECT_LEARNINGS.md` | Safe repo-relative Markdown path for the machine-managed learnings ledger, overriding the `.lisa/` default. Rejected if it resolves inside any auto-loaded rules tree (`.claude/rules`, `.cursor/rules`, `.github/instructions`, `.agents/rules`) — the ledger must stay out of eager context. |
 | `usage` | no | — | Optional token/cost pricing metadata consumed by the `usage-accounting` rule. Missing pricing never blocks a lifecycle flow; Lisa records token counts with `estimated_cost: null` when no trustworthy price source is configured. |
 | `wiki` | no | — | Wiki location for the `wiki-knowledge-source` rule. Omit for a local in-repo wiki (`wiki/`). See **Wiki source** below. |
 

package/plugins/src/base/rules/reference/intent-routing.md

@@ -166,6 +166,8 @@ Determine the work type and execute the matching variant:
 3. Recommend next action (Research, Plan, Implement, or escalate)
 4. `learner` -- capture discoveries
 
+In every work type above, before a task completes -- immediately ahead of the closing `learner` step -- the implementing agent records concise kind-tagged MLD (Mistakes / Learnings / Desires) into that task's `metadata.learnings`: one line per item, empty is valid, never re-prompted or scored. See the `lisa-implement` skill for the full `{ kind, note, evidence? }` schema and routing (change the schema there, not here).
+
 Output: Code passing all quality gates + local empirical verification + codified regression test for each verification (except for spikes, which produce findings only, and non-behavioral verification types — PR / Documentation / Deploy — which carry their own proof).
 
 ### Verify

package/plugins/src/base/rules/reference/project-learnings.md

@@ -1,14 +1,21 @@
 # Project Learnings
 
-Project learnings are Lisa's bounded, repo-local memory surface. They are stored
-in `PROJECT_LEARNINGS.md`, derived as the sibling of the configured
-`.lisa.config.json` `projectRulesFile` value. With no config override, the path
-is `.claude/rules/PROJECT_LEARNINGS.md`.
+Project learnings are Lisa's bounded, repo-local memory surface. The
+machine-managed ledger is `PROJECT_LEARNINGS.md`, resolved from
+`.lisa.config.json`: the optional `learnings.file` override, else the default
+`.lisa/PROJECT_LEARNINGS.md`. The ledger deliberately lives in the cold `.lisa/`
+directory — **not** under `.claude/rules/` or any other auto-loaded rules tree —
+because anything in those trees is injected raw into every session, which
+double-loads the file and bypasses the contract's budget and validation.
 
-Consume learnings before normal task work whenever the file exists. Use the
-executable contract from `@codyswann/lisa/learnings` to parse, validate, and
-budget-check the document. Do not duplicate numeric caps in rules or prompts;
-the exported contract is the source of truth.
+Consume learnings before normal task work whenever the file exists, and consume
+them ONLY through the executable contract from `@codyswann/lisa/learnings`:
+`parseLearningsFile` to parse and validate, then `projectLearnings` to take the
+bounded serving slice (the highest-priority entries — ordered by confidence,
+then recency — that fit the token/entry budget, plus how many were omitted).
+**Never read the raw ledger file wholesale into context**; the session receives
+the bounded projection, not the full document. Do not duplicate numeric caps in
+rules or prompts; the exported contract is the source of truth.
 
 Each persisted entry has seven fields:
 
@@ -50,6 +57,19 @@ Precedence:
 3. Project learnings add recent operational knowledge, but never rewrite or
    append to `PROJECT_RULES.md`.
 
+## Task telemetry (MLD) is not context
+
+Raw task-end MLD telemetry — the Mistakes / Learnings / Desires an implementing
+agent records into `metadata.learnings`, and the raw yield of debrief mining — is
+rung-1 capture only: it is never read into a later session's instruction surface,
+never required of an agent (empty is valid), and never graded or scored. It reaches
+a durable surface only indirectly — through the learner's validation into the
+ledger (which sessions still consume solely as the bounded projection above), and
+from there through the gardener's ticket-gated promotion a human approved. Injecting
+raw self-reports, or treating their volume as a quality signal, would reward
+plausible commentary over good outcomes and bypass the very budget and validation
+this contract exists to enforce.
+
 Antigravity note: agy does not receive the plugin `rules/` tree. Lisa reconciles
 a bounded `AGENTS.md` bridge that points agy at this same file without copying
 learning bodies or restoring the retired full rules bake.

package/plugins/src/base/skills/lisa-implement/SKILL.md

@@ -161,7 +161,7 @@ Every task MUST include this JSON metadata block. Do NOT omit `skills` (use `[]`
   "relevant_documentation": "",
   "testing_requirements": ["..."],
   "skills": ["..."],
-  "learnings": ["..."],
+  "learnings": [{ "kind": "mistake", "note": "one line", "evidence": "optional ref" }],
   "required_access": [
     { "tool": "<external tool/system this task or its verification needs>", "probe": "<the read-only command or *-access check that proves access>", "status": "pass|fail" }
   ],
@@ -173,11 +173,16 @@ Every task MUST include this JSON metadata block. Do NOT omit `skills` (use `[]`
 }
 ```
 
+The `learnings` array is task-end MLD telemetry (Mistakes / Learnings / Desires) — a low-trust self-report for the harness builder, never instructions for a later agent. Each entry is either a plain string (treated as kind `learning` for backward compatibility with older flows) or an object, exactly like the example entry in the block above: a `kind` of `mistake`, `learning`, or `desire`; a one-line `note`; and an optional `evidence` pointer. A `mistake` is an error in the agent's own trajectory, a `learning` is an environment fact discovered the hard way, a `desire` is context or tooling the agent wished it had. Keep each to one line — no essays. `mistake`/`learning` entries are ledger candidates; `desire` entries are tooling-gap candidates that the learner (#1731) records for the gardener's human-gated tooling-gap lane.
+
 Before any task is implemented, the agent team must explore the codebase for relevant research (documentation, code, git history, etc) and update each task's `metadata.relevant_documentation` with the findings.
 
 For Fix tasks and user-visible Build tasks, `testing_requirements` must include the highest-practical-observation regression requirement above, including the selected harness or the recorded absence/blocker path. The completion condition must include the proof command and the required CI execution evidence for the new spec.
 
 Each task must be reviewed by the team to make sure their verification passes.
+
+Before marking a task complete, the implementing agent records concise MLD into `metadata.learnings` — mistakes (errors in its own trajectory), learnings (environment facts it discovered the hard way), and desires (context or tools it wished it had). Empty (`learnings: []`) is a valid result: never re-prompt for content, and never grade or score self-reports — a scored MLD would reward plausible self-commentary over good outcomes.
+
 Each task must have their learnings reviewed by the learner subagent.
 
 Before shutting down the team, execute the Verify flow:

package/plugins/src/base/skills/lisa-persist-learning/SKILL.md

@@ -139,7 +139,7 @@ Continue to Phase 3.
 No learning content is ever committed without a PR — there is no other write path, and the PR must touch **only** the learnings surface (any other changed file is a bug).
 
 1. **PR dedupe.** Search all PRs for the marker `[lisa-learning-pr] key=<fingerprint>` in the body (`gh pr list --state all --search '"<marker>" in:body' --json number,url`), with the stale-index guard above. If one exists, reference it and stop — never open a duplicate.
-2. **Resolve the learnings surface path — never hardcode it.** The canonical path is `resolveProjectLearningsFile` from `@codyswann/lisa/learnings`: the `PROJECT_LEARNINGS.md` sibling of the configured `.lisa.config.json` `projectRulesFile` (default `.claude/rules/PROJECT_LEARNINGS.md`):
+2. **Resolve the learnings surface path — never hardcode it.** The canonical path is `resolveProjectLearningsFile` from `@codyswann/lisa/learnings`: the machine-managed ledger resolved from `.lisa.config.json` (the `learnings.file` override, else the default `.lisa/PROJECT_LEARNINGS.md` — a cold path, never an auto-loaded rules tree):
 
    ```bash
    LEARNINGS_FILE=$(node -e 'import("@codyswann/lisa/learnings").then(async m => { const c = await m.readProjectConfig(process.cwd()); console.log(m.resolveProjectLearningsFile(c)); })')

package/scripts/check-learnings-budget.ts

@@ -14,8 +14,7 @@ const DEFAULT_LEARNINGS_FILE = path.resolve(
   "..",
   "all",
   "create-only",
-  ".claude",
-  "rules",
+  ".lisa",
   "PROJECT_LEARNINGS.md"
 );