kodelyth-ecc 1.8.0 → 1.8.2

package/docs/dashboard.md

@@ -1,211 +0,0 @@
-# Local observability dashboard
-
-> A localhost-only single-page web UI that renders every local data source Kodelyth ECC produces. Zero telemetry. Zero external runtime dependencies. Read-only.
-
----
-
-## Why it exists
-
-ECC produces a lot of local state by default:
-
-- BM25 memory captures (`~/.kodelyth/memory/`)
-- Self-evolving memory signals + proposals (`~/.kodelyth/evolve/`)
-- Token-budget hook state (`~/.kodelyth/token-budget/`)
-- Swarm/orchestration session dirs (`.orchestration/<session>/`)
-- The full catalog of shipped agents / skills / commands / rules / bundles
-
-The only way to see all of this was to read JSON files by hand or run six different CLI subcommands. The dashboard is the one-glance answer.
-
----
-
-## Boot
-
-```bash
-npx kodelyth-ecc dashboard                        # default: 127.0.0.1:5747, auto-opens browser
-npx kodelyth-ecc dashboard --port 8088            # custom port
-npx kodelyth-ecc dashboard --no-open              # don't auto-open browser (CI / remote shells)
-npx kodelyth-ecc dashboard --host localhost       # explicit localhost binding
-```
-
-Press `Ctrl+C` to stop. The server has no daemon mode by design — it lives only as long as your terminal session.
-
----
-
-## Localhost lock
-
-The dashboard exposes everything the BM25 store and evolve log have ever recorded. Memories may contain code, problem statements, project paths, gotchas. The default bind is `127.0.0.1` and the server **refuses** to start on any other interface unless you explicitly opt out:
-
-```bash
-KODELYTH_DASHBOARD_ALLOW_REMOTE=1 \
-  npx kodelyth-ecc dashboard --host 0.0.0.0
-```
-
-This escape hatch is intentionally inconvenient. Don't use it on a network you don't fully control.
-
-Without the env var, attempting any non-localhost host produces:
-
-```
-[dashboard] refusing to bind host=0.0.0.0. Dashboard is localhost-only by default.
-To override (UNSAFE — exposes your memory + evolve data), set KODELYTH_DASHBOARD_ALLOW_REMOTE=1.
-```
-
----
-
-## What you see
-
-### Overview tab
-
-A wall of stat cards: agents · skills · commands · rules · bundles · captured memories · surfaces · routing misses · pending proposals · swarm sessions. Plus storage paths and a token-budget snapshot.
-
-### Memory tab
-
-- Stats: total / projects / language count / tag classes
-- BM25 search box (proxies through `/api/memory/search`)
-- Recent captures table with tags + source
-
-### Evolve tab
-
-- Reuse + miss + proposal counts
-- Top 10 reused memories with surface count and last-seen
-- Top 10 miss clusters with token tags and a sample prompt
-- Proposals table with status pills (`pending` / `accepted` / `rejected` / `applied`)
-
-### Catalog tab
-
-- Selector for agents / skills / commands / rules / bundles
-- Free-text filter across name, description, tags
-- Tabular results with up to 200 entries per page
-
-### Sessions tab
-
-- Lists every swarm session in `.orchestration/`
-- Per-session: workers, modified time, expandable detail with `task.md` + `handoff.md` + `status.md` excerpts
-
----
-
-## API surface
-
-The frontend is just a consumer of these endpoints. They're curl-friendly:
-
-| Endpoint | Returns |
-|---|---|
-| `GET /api/health` | `{ ok: true, time: <iso> }` — liveness probe |
-| `GET /api/overview` | counts + storage paths |
-| `GET /api/memory[?limit=N]` | `{ stats, recent }` |
-| `GET /api/memory/search?q=…[&limit=N]` | `{ query, results }` |
-| `GET /api/evolve[?limit=N]` | `{ reuse, miss, proposals }` |
-| `GET /api/catalog?kind=…[&q=…&limit=N]` | `{ kind, counts, items }` (kind ∈ agents/skills/commands/rules/bundles) |
-| `GET /api/sessions[?limit=N]` | `{ sessions }` |
-| `GET /api/sessions/:name` | `{ session, path, workers }` |
-| `GET /api/token-budget` | `{ sessions, total_tokens }` |
-
-### Examples
-
-```bash
-# Last 5 captured memories
-curl -s http://127.0.0.1:5747/api/memory?limit=5 | jq '.recent'
-
-# Search memory for "tailwind v4"
-curl -s 'http://127.0.0.1:5747/api/memory/search?q=tailwind+v4' | jq '.results'
-
-# Pending proposals
-curl -s http://127.0.0.1:5747/api/evolve | jq '.proposals[] | select(.status == "pending")'
-
-# All agents whose tags include "security"
-curl -s 'http://127.0.0.1:5747/api/catalog?kind=agents&q=security'
-```
-
----
-
-## Hard rules (enforced by the server)
-
-1. **GET-only.** Any other method returns `405 method not allowed`. The dashboard CANNOT mutate state.
-2. **Localhost lock.** Non-localhost binds refused without `KODELYTH_DASHBOARD_ALLOW_REMOTE=1`.
-3. **Path-traversal-safe.** Static file resolution is sandboxed under `scripts/dashboard/static/`. `../` and similar are rejected.
-4. **No cache.** Every response carries `Cache-Control: no-store`. Data is always fresh.
-5. **Hardened headers.** `X-Frame-Options: DENY`, `X-Content-Type-Options: nosniff`, `Referrer-Policy: no-referrer` on every response.
-6. **No external assets.** No CDNs, no Google Fonts, no analytics. Works fully offline.
-7. **Defensive aggregation.** Every data-source read is wrapped in try/catch with empty-default fallback. A broken memory store renders empty cards, never a 500.
-
----
-
-## Architecture
-
-```
-scripts/dashboard/
-├── server.js          ← HTTP server. Routes API + static files.
-├── data.js            ← Pure aggregators. Reads memory + evolve + catalog + sessions + budget.
-└── static/
-    └── index.html     ← Single-page UI. Hand-rolled CSS + vanilla JS. No build step.
-```
-
-### `data.js`
-
-Pure functions only. Every aggregator:
-
-- Accepts its data-source paths as explicit arguments OR uses well-defined env-overridable defaults
-- Returns sane empty defaults on failure (never throws)
-- Has no global mutable state
-- Is unit-testable in isolation
-
-### `server.js`
-
-Uses only Node built-ins:
-
-- `http` for the listener
-- `fs`, `path` for static files
-- `child_process.execFileSync` for browser auto-open (`open` / `xdg-open` / `cmd /c start`) — no shell interpolation
-
-No `express`, no `koa`, no third-party static-file middleware. All hardening is hand-rolled and auditable in ~290 lines.
-
-### `index.html`
-
-- Hand-rolled CSS (no Tailwind, no CDN)
-- Vanilla JS with `fetch` → no build step, no transpilation
-- Tabs are simple data-attribute toggles
-- Lazy-loads each tab's data only when shown
-- SSE (`/api/events`) pushes `data-changed` events when watched files change; a `heartbeat` every 10 s keeps the green dot alive without triggering data reloads
-
----
-
-## Worked example
-
-```bash
-$ npx kodelyth-ecc dashboard --port 5747
-✓ Kodelyth ECC dashboard
-  http://127.0.0.1:5747/
-  Press Ctrl+C to stop. Localhost only — zero telemetry.
-```
-
-In another shell:
-
-```bash
-$ curl -s http://127.0.0.1:5747/api/overview | jq '.catalog'
-{
-  "agents": 70,
-  "skills": 193,
-  "commands": 96,
-  "rules": 14,
-  "bundles": 3
-}
-```
-
----
-
-## Composition with other features
-
-| Feature | Effect on the dashboard |
-|---|---|
-| **Memory store** | Source of the Memory tab. |
-| **Swarm orchestrator** | Source of the Sessions tab. |
-| **Token-budget hook** | Source of the budget snapshot card. |
-| **Self-evolving memory** | Source of the Evolve tab. Proposals appear automatically as they're generated. |
-
----
-
-## See also
-
-- `skills/observability-dashboard/SKILL.md` — explicit-invocation skill
-- `commands/dashboard.md` — `/dashboard` slash command
-- `scripts/dashboard/{server,data}.js` — implementation
-- `tests/dashboard/` — aggregator + server smoke tests

package/docs/evolve.md

@@ -1,303 +0,0 @@
-# Self-evolving memory
-
-> Phase 3.4 of the Devil Roadmap. Closes the learning loop on the BM25 memory system. Repeated memory hits become draft skills. Repeated routing misses become proposed routing-rule additions. Nothing is ever auto-applied.
-
----
-
-## Why this exists
-
-ECC already has:
-
-- A BM25 memory store (`scripts/memory/store.js`)
-- An auto-recall hook that surfaces relevant memories on every `UserPromptSubmit`
-
-What it didn't have, until 3.4: a way for those signals to feed back into the toolkit's own structure. If the same memory keeps getting surfaced across sessions, that memory is doing real work — it should graduate to a `SKILL.md`. If users keep submitting prompts that match no memory at all, that's a routing gap — the routing rule should grow.
-
-The 3.4 surface formalizes both loops while preserving the **never auto-commit** rule.
-
----
-
-## Two signal streams
-
-### 1. Memory reuse (→ skill-upgrade proposals)
-
-Every time `auto-recall.js` surfaces a memory to the user, it bumps a counter:
-
-```jsonc
-// ~/.kodelyth/evolve/reuse.json
-{
-  "byMemory": {
-    "<memoryId>": {
-      "count": 7,
-      "sessions": ["s1", "s2", "s3", ...],
-      "projects": ["/path/to/proj-a", "/path/to/proj-b"],
-      "firstSurfaced": "2026-04-30T...",
-      "lastSurfaced":  "2026-05-10T..."
-    }
-  },
-  "lastUpdated": "2026-05-10T..."
-}
-```
-
-Counter semantics:
-
-- **Per-memory, per-session**: surfacing the same memory ten times in one session counts ONCE. Matches the existing "never re-surface the same memory twice in a session" rule of `auto-recall.js`.
-- **Cross-session**: each fresh session bumps the count by exactly one.
-- **Idempotent**: replaying a session does not double-count.
-
-Default threshold: count ≥ 3 AND sessions ≥ 2 → eligible for skill-upgrade proposal.
-
-### 2. Routing misses (→ routing-addition proposals)
-
-When `shouldRecall(prompt)` is true (substantive prompt, ≥12 chars, ≥2 meaningful tokens, not a slash command) AND BM25 recall returns zero matches, the prompt is logged:
-
-```jsonl
-// ~/.kodelyth/evolve/routing-misses.jsonl  (append-only)
-{"hash":"abc...","prompt":"...","tokens":["..."],"session_id":"...","project":"...","recorded_at":"..."}
-```
-
-Stored prompts are capped at 1000 chars. Top tokens are extracted at write time so analysis is cheap.
-
-Default threshold: cluster count ≥ 3 AND distinct prompts ≥ 2 → eligible for routing-addition proposal.
-
----
-
-## CLI
-
-### `kodelyth-ecc evolve stats`
-
-Snapshot of recorded signals. No proposals generated.
-
-```
-Kodelyth ECC — self-evolving memory stats
-  reuse:
-    memories tracked: 14
-    total surfaces:   42
-    last updated:     2026-05-10T17:23:00.000Z
-    top reused:
-      • efe17d650917e445  count=7  sessions=5
-      • a91ce2034d8b1234  count=5  sessions=4
-  routing misses:
-    total:            18
-    unique prompts:   11
-    top clusters:
-      • count=4  tokens=[feature, flag, gradual, rollout]
-      • count=3  tokens=[migration, postgres, downtime, zero]
-```
-
-### `kodelyth-ecc evolve analyze`
-
-Apply thresholds and write proposals. Idempotent — same evidence produces the same proposal ID, so re-running never duplicates.
-
-| Flag | Default | Effect |
-|---|---|---|
-| `--reuse-min N` | 3 | minimum total surface count |
-| `--reuse-min-sessions N` | 2 | minimum distinct sessions |
-| `--miss-min N` | 3 | minimum miss-cluster total |
-| `--miss-min-distinct N` | 2 | minimum distinct prompts in cluster |
-| `--json` | off | full report instead of pretty summary |
-
-### `kodelyth-ecc evolve list [--status pending|accepted|rejected|applied]`
-
-Show proposals. Filter by status. Pretty output uses ⏸ ✓ ✗ ★ marks for the four states.
-
-### `kodelyth-ecc evolve show <id>`
-
-Print the full proposed file content + evidence. **Always preview before accepting.**
-
-### `kodelyth-ecc evolve accept <id> [--root DIR] [--overwrite]`
-
-Write the proposed `diff` to its `target_path` under `--root`. Refuses to overwrite an existing file unless `--overwrite` is explicit. Marks the proposal `accepted` with the absolute `applied_path` written to the audit trail.
-
-**The CLI does not stage, does not commit, does not push.** Review the draft, edit, commit by hand.
-
-### `kodelyth-ecc evolve reject <id> [--note "..."]`
-
-Mark a proposal `rejected`. The optional `--note` is preserved in the audit trail for future reference.
-
----
-
-## Proposal anatomy
-
-Both proposal kinds share a structure:
-
-```jsonc
-{
-  "id": "skill-2537cb787a",          // deterministic over evidence
-  "type": "skill-upgrade",            // or "routing-addition"
-  "evidence": {
-    "memoryId": "efe17d650917e445",
-    "reuseCount": 7,
-    "sessions": ["s1", "s2", "s3", "s4", "s5"],
-    "firstSurfaced": "...",
-    "lastSurfaced": "..."
-  },
-  "proposal": {
-    "kind": "create-skill",                                            // or "add-routing-entry"
-    "target_path": "skills/<slug>/SKILL.md",                           // for skill-upgrade
-    "diff": "<full markdown content>",
-    "rationale": "Memory '...' surfaced 7x across 5 sessions ..."
-  },
-  "status": "pending",                // pending | accepted | rejected | applied
-  "created_at": "...",
-  "timestamp": "...",
-  "applied_path": null                // set on accept
-}
-```
-
-### Skill-upgrade diff (sample)
-
-```markdown
----
-name: <slug-from-problem>
-description: <problem text> (auto-derived from memory <id> after repeated reuse)
-origin: kodelyth-evolve
-language: typescript
-tags:
-  - <memory tags>
----
-
-# Skill: <slug>
-
-> **Auto-derived draft.** Generated by `kodelyth-ecc evolve` after this memory
-> was surfaced repeatedly across multiple sessions. Review, refine, and rename
-> before committing.
-
-## Problem
-<memory.problem>
-
-## Approach
-<memory.approach>
-
-## Gotchas
-<memory.gotchas if any>
-
-## When to invoke
-_Replace this section with explicit trigger conditions._
-
-## Origin
-- Memory id: `<id>`
-- Captured at: <timestamp>
-- Auto-promoted by Phase 3.4 self-evolving memory.
-```
-
-### Routing-addition diff (sample)
-
-```markdown
-<!-- proposed addition to rules/common/agent-intent-routing.md -->
-<!-- review by hand, decide on tier + agent, then merge -->
-
-### TODO-agent — covers prompts about <token>, <token>, <token>
-
-Trigger if the user mentions `<t1>`, `<t2>`, `<t3>`.
-
-| Signal | Real human phrasing |
-|---|---|
-| repeated unrouted prompt cluster | <tokens> |
-
-**Origin:** Phase 3.4 self-evolving memory — N prompts in this cluster were
-submitted with no memory match and (presumably) no specialist routing.
-
-Recent samples:
-  - "<sample 1>"
-  - "<sample 2>"
-  - "<sample 3>"
-
-_(Pick the right tier in `rules/common/agent-intent-routing.md` before merging.
-Do NOT commit this block as-is — replace `TODO-agent` with the real agent name
-and slot under the correct priority tier.)_
-```
-
-The `TODO-agent` placeholder is intentional. Even if you accept and commit verbatim, the rule won't route any real traffic — it's a no-op until you fill in the agent name.
-
----
-
-## Storage layout
-
-```
-~/.kodelyth/evolve/                        ← override with $KODELYTH_EVOLVE_DIR
-├── reuse.json                             ← per-memory reuse counters
-├── routing-misses.jsonl                   ← append-only miss log
-└── proposals.jsonl                        ← append-only proposal events
-```
-
-`proposals.jsonl` is append-only. Every state transition is a new event. Reading collapses to "latest state per id" while preserving the full history for audit.
-
----
-
-## Worked example
-
-```bash
-# 1) Use ECC normally for a few weeks. The auto-recall hook records signals.
-# 2) Eventually run:
-$ npx kodelyth-ecc evolve stats
-... shows current signal volume ...
-
-# 3) Generate proposals.
-$ npx kodelyth-ecc evolve analyze
-✓ analyzed signals
-  reuse entries scanned:  14
-  miss entries scanned:   11
-  proposals generated:    3
-  new proposals (added):  3
-
-  Run 'kodelyth-ecc evolve list' to review.
-
-# 4) See what's pending.
-$ npx kodelyth-ecc evolve list
-Kodelyth ECC — self-evolving memory proposals (3)
-  ⏸ [pending] skill-2537cb787a  skill-upgrade
-     target: skills/tailwind-v4-arbitrary-values/SKILL.md
-     why:    Memory '...' surfaced 7x across 5 sessions ...
-  ⏸ [pending] route-13d976a554  routing-addition
-     target: rules/common/agent-intent-routing.md
-     why:    4 substantive prompts (4 distinct) clustered on tokens [...]
-
-# 5) Inspect the skill draft.
-$ npx kodelyth-ecc evolve show skill-2537cb787a
-... full markdown + evidence ...
-
-# 6) Accept it. Writes to disk. NEVER commits.
-$ npx kodelyth-ecc evolve accept skill-2537cb787a
-✓ accepted skill-2537cb787a
-  draft written: /path/to/repo/skills/tailwind-v4-arbitrary-values/SKILL.md
-
-  Review the draft. When you're happy with it, commit it.
-
-# 7) Reject the routing one — already covered.
-$ npx kodelyth-ecc evolve reject route-13d976a554 --note "covered by debug-detective"
-✗ rejected route-13d976a554 (note: covered by debug-detective)
-```
-
----
-
-## Hard rules
-
-1. **NEVER auto-apply.** `accept` writes a draft. The user reviews, edits, commits.
-2. **NEVER overwrite without `--overwrite`.** Even on accept of a stale proposal.
-3. **NEVER block the recall hook.** All evolve recording is wrapped in try/catch and lazy-required.
-4. **NEVER auto-route a `TODO-agent` proposal.** The placeholder is intentional.
-5. **Idempotent IDs.** Stable evidence → stable proposal ID. Re-running `analyze` never duplicates.
-6. **Append-only proposal log.** Every state change is a new event. Full audit trail preserved.
-
----
-
-## Composition with other phases
-
-| Pair | Effect |
-|---|---|
-| BM25 memory store | Source of reuse signals. |
-| `/memory remember` | Manually captured memories that get reused → skill proposals. |
-| `rules/common/agent-intent-routing.md` | Direct target for routing-addition proposals. |
-| Phase 2.7 swarm | Repeated swarm tasks reusing the same memories → those memories become skills the swarm picker can choose automatically. |
-| Phase 2.8 replay | Replay bundles re-trigger reuse signals when the same memory is surfaced again. |
-| Phase 2.10 token-budget hook | Promoting memories → skills means cheaper recalls. |
-
----
-
-## See also
-
-- `skills/self-evolving-memory/SKILL.md` — explicit-invocation skill
-- `commands/memory-evolve.md` — `/memory-evolve` slash command
-- `scripts/evolve/{stats,analyze,proposals}.js` — pure-function implementation
-- `hooks/memory/auto-recall.js` — signal capture (Phase 3.4 augmentation)

package/docs/mcp-clients.md

@@ -1,167 +0,0 @@
-# Kodelyth ECC — MCP Client Mode
-
-The other half of the MCP story. While `npx kodelyth-ecc mcp` (Phase 2.1) **serves** ECC to any MCP-compatible client, MCP client mode lets ECC **consume** any external MCP server — Stripe, GitHub, Postgres, Redis, Brave, Filesystem, Shopify, Sentry, anything.
-
-> **Phase 2.5 of the [Devil Roadmap](../README.md).** This makes ECC the MCP **hub**, not just a node. Local-only registry. Zero telemetry. Same SDK as the server side.
-
----
-
-## Quick start
-
-### 1. Register an external MCP server
-
-```bash
-# Public servers (no env vars needed)
-npx kodelyth-ecc mcp-add brave -- npx -y @modelcontextprotocol/server-brave-search
-npx kodelyth-ecc mcp-add filesystem -- npx -y @modelcontextprotocol/server-filesystem /Users/me/notes
-
-# Servers that need credentials
-npx kodelyth-ecc mcp-add github \
-  --env GITHUB_PERSONAL_ACCESS_TOKEN=ghp_... \
-  --desc "ECC project ops on github" \
-  -- npx -y @modelcontextprotocol/server-github
-
-npx kodelyth-ecc mcp-add postgres \
-  --env DB_URL=postgres://localhost/myapp \
-  -- npx -y @modelcontextprotocol/server-postgres
-
-npx kodelyth-ecc mcp-add stripe \
-  --env STRIPE_API_KEY=sk_... \
-  -- npx -y @stripe/mcp
-```
-
-The registry is stored at `~/.kodelyth/mcp-clients.json` (override with `KODELYTH_MCP_CLIENT_DIR`).
-
-### 2. Inspect a registered server
-
-```bash
-npx kodelyth-ecc mcp-list                       # all registered
-npx kodelyth-ecc mcp-tools github               # tools the server exposes
-npx kodelyth-ecc mcp-resources filesystem       # resources
-npx kodelyth-ecc mcp-prompts brave              # prompts
-```
-
-### 3. Call a tool
-
-```bash
-# No args:
-npx kodelyth-ecc mcp-call github list_repos
-
-# JSON args:
-npx kodelyth-ecc mcp-call github create_issue \
-  --json '{"owner":"sifxprime","repo":"kodelyth-ecc","title":"hi from ECC"}'
-
-npx kodelyth-ecc mcp-call postgres query \
-  --json '{"sql":"SELECT count(*) FROM users"}'
-```
-
-### 4. Unregister
-
-```bash
-npx kodelyth-ecc mcp-remove github
-```
-
----
-
-## CLI surface
-
-| Command | Description |
-|---|---|
-| `mcp-add <name> [--env K=V] [--desc "..."] -- <command> [args...]` | Register an external server. |
-| `mcp-list` | List registered servers. |
-| `mcp-remove <name>` | Unregister. |
-| `mcp-tools <name>` | List tools exposed by the server. |
-| `mcp-resources <name>` | List resources. |
-| `mcp-prompts <name>` | List prompts. |
-| `mcp-call <name> <tool> [--json '{"arg":"value"}']` | Call a tool with JSON arguments. |
-
-The `--` separator before the command is mandatory in `mcp-add` so the registry can disambiguate flags belonging to ECC from flags meant for the external server.
-
----
-
-## Programmatic use
-
-The same registry powers in-session agent tool calls. Inside an ECC agent or skill, require the client library:
-
-```js
-const client = require('kodelyth-ecc/scripts/mcp/client.js');
-
-// Open a stable connection.
-const session = await client.connect('github');
-const out = await session.client.callTool({
-  name: 'create_issue',
-  arguments: { owner: 'sifxprime', repo: 'kodelyth-ecc', title: 'auto-issue' },
-});
-await session.close();
-
-// Or one-shot:
-const tools = await client.listTools('postgres');
-const stats = await client.callTool('redis', 'set', { key: 'k', value: 'v' });
-```
-
-Every call spawns a fresh stdio subprocess; there's no long-lived process pool. This is intentional — failed servers don't poison subsequent calls, and credentials live only in the per-call env.
-
----
-
-## Registry shape
-
-```json
-{
-  "servers": {
-    "github": {
-      "name": "github",
-      "command": "npx",
-      "args": ["-y", "@modelcontextprotocol/server-github"],
-      "env":  { "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_..." },
-      "description": "ECC project ops on github",
-      "added_at": "2026-05-10T10:48:00.690Z"
-    }
-  }
-}
-```
-
-You can hand-edit the file. Reserved name patterns: alphanumeric, dash, underscore.
-
----
-
-## Pairing with the rest of ECC
-
-| Pairs with | How |
-|---|---|
-| **Phase 2.1 — MCP server** | The two halves complete each other. ECC serves to any framework AND consumes from any provider. |
-| **Phase 2.10 — prompt-injection-guard** | Tool responses from external MCP servers are scanned for indirect injection on `PostToolUse:mcp__*` (opt in via `KODELYTH_PI_GUARD=warn|block`). |
-| **Phase 2.4 — cost-aware model router** | Tool responses are part of the session token-budget when the safety hook is enabled. |
-| **kodelyth-memory** | Capture interesting tool responses as memories with `kodelyth-ecc remember "..." --approach "..."`. |
-
----
-
-## Privacy & safety
-
-- **No network egress from this client** — it only spawns subprocesses you registered.
-- **Credentials live in the registry file.** Treat `~/.kodelyth/mcp-clients.json` like a secrets file. `chmod 600` is recommended on shared machines.
-- **External servers can do whatever the user gives them permission to do** — register only servers you trust.
-- **Pair with `prompt-injection-guard`** to scan tool responses for indirect injection before agents act on them.
-
----
-
-## Troubleshooting
-
-**"Kodelyth MCP client requires `@modelcontextprotocol/sdk`"** — run `npm install @modelcontextprotocol/sdk` once, or rerun via `npx -y kodelyth-ecc ...`.
-
-**"MCP server X is not registered"** — `mcp-list` shows nothing because the registry lives at `~/.kodelyth/mcp-clients.json` (or `$KODELYTH_MCP_CLIENT_DIR`). Re-run `mcp-add`.
-
-**Server hangs on connect** — the external server probably needs env vars you didn't pass. Re-add with `--env KEY=VAL`.
-
-**Tool call returns `isError: true`** — the external server rejected the call. Inspect the `content[0].text` for the underlying error message; it's typed exactly as the spec.
-
----
-
-## Roadmap interactions
-
-- **Phase 2.6 — sandbox layer** will wrap external MCP servers in Docker/firejail isolation by default.
-- **Phase 2.3 — local dashboard** will show live MCP traffic per registered server (count, latency, errors).
-- **Phase 2.9 — SLSA/SBOM** will publish provenance for the ECC server side and let `supply-chain-auditor` verify external server packages.
-
----
-
-Built into [Kodelyth ECC](../README.md). MIT licensed. PRs welcome.