loki-mode 7.30.0 → 7.31.0
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/README.md +4 -2
- package/SKILL.md +2 -2
- package/VERSION +1 -1
- package/autonomy/context-tracker.py +8 -0
- package/autonomy/loki +462 -105
- package/autonomy/mcp-launch.sh +124 -22
- package/autonomy/run.sh +148 -1
- package/bin/loki +19 -0
- package/dashboard/__init__.py +1 -1
- package/dashboard/server.py +226 -1
- package/dashboard/static/index.html +105 -39
- package/docs/INSTALLATION.md +1 -1
- package/docs/competitive/replit-lovable-analysis.md +1 -1
- package/loki-ts/data/model-pricing.json +1 -0
- package/loki-ts/dist/loki.js +233 -232
- package/mcp/__init__.py +1 -1
- package/mcp/_sdk_loader.py +157 -0
- package/mcp/lsp_proxy.py +61 -61
- package/mcp/server.py +14 -129
- package/package.json +1 -1
- package/providers/claude.sh +76 -19
- package/providers/model_catalog.json +9 -0
- package/skills/model-selection.md +44 -0
package/README.md
CHANGED
|
@@ -28,6 +28,8 @@
|
|
|
28
28
|
- **Production quality built in** -- 11 quality gates (`skills/quality-gates.md`), blind 3-reviewer code review (`run.sh:run_code_review()`), anti-sycophancy checks
|
|
29
29
|
- **Standalone verification: `loki verify`** -- Run Loki's deterministic gates (build, tests, static analysis, secret scan, dependency audit) against any branch or PR diff, including code written by other agents or humans. CI-ready exit codes (0 VERIFIED, 1 CONCERNS, 2 BLOCKED), machine-readable evidence at `.loki/verify/evidence.json`. Inconclusive evidence is never reported as VERIFIED (v7.27.0).
|
|
30
30
|
- **Living spec and pre-build interrogation** -- `loki spec` locks a spec and detects drift deterministically (`spec.lock`, `drift-report.json`, and a `SPEC_DRIFT` finding in `loki verify` with CI exit codes), so you can tell when the build diverges from what was agreed. `loki grill` runs a Devil's-Advocate interrogation of the spec before you build, surfacing gaps and contradictions early (v7.28.0).
|
|
31
|
+
- **Mid-flight model switching + Claude Fable tier** -- switch the model a live run uses from the dashboard (applies at the next iteration, current run only), with Claude Fable available as a premium tier at its published $10/$50 per MTok (2x Opus). For every model lever (session pin to Fable, mid-flight override, architect pass) and every `LOKI_MAX_TIER` path, the `loki plan` quote, the dashboard's reported model, and the actual dispatched model agree, with the ceiling enforced (v7.31.0).
|
|
32
|
+
- **A calmer CLI** -- the help surface is ~20 grouped workflow entries instead of a 70-command wall; merged commands live on as aliases that forward byte-identically with a one-line stderr pointer, so no script breaks (v7.31.0).
|
|
31
33
|
- **Guided first build: `loki quickstart`** -- four quick questions (setup check, one-line idea, template pick, plan review) and your build starts; pressing Enter through every step builds the sample Todo app. The plan step quotes the real cost/time estimate before anything is spent, and `loki demo` now confirms its estimate the same way. If no AI provider CLI is installed, Loki offers to install Claude Code (consent-gated, interactive terminals only) (v7.29.0).
|
|
32
34
|
- **Live App Preview** -- The dashboard embeds the locally-running app in an iframe so you can interact with it immediately during a build. Use `loki preview` (alias `loki open`) to print the URL and open it in your browser. Local-first: no hosted service, no vendor lock (v7.24.0).
|
|
33
35
|
- **Compose-first fullstack** -- When a spec needs more than one service (web + database + cache) Loki generates a 12-factor `docker-compose.yml` with healthchecks, `depends_on` wiring, env-var config, and a `.env.example`. The Live App Preview surfaces the web service URL (not a database port), and health reflects the web service's Docker healthcheck so a crashed app shows as crashed even when the database stays up. Single-service apps stay on a plain run command. All local-first, no hosted service (v7.26.0).
|
|
@@ -102,7 +104,7 @@ loki quick "build a landing page with a signup form"
|
|
|
102
104
|
|--------|---------|-------|
|
|
103
105
|
| **Bun (recommended)** | `bun install -g loki-mode` | Fastest startup for CLI commands. |
|
|
104
106
|
| **Homebrew** | `brew tap asklokesh/tap && brew install loki-mode` | Auto-installs Bun as a dep |
|
|
105
|
-
| **Docker** | `docker pull asklokesh/loki-mode:7.
|
|
107
|
+
| **Docker** | `docker pull asklokesh/loki-mode:7.31.0 && docker run --rm asklokesh/loki-mode:7.31.0 start prd.md` | Bun pre-installed in image |
|
|
106
108
|
| **npm (compat)** | `npm install -g loki-mode` | Works without Bun (bash fallback). Migrate any time with `loki self-update --to bun`. |
|
|
107
109
|
|
|
108
110
|
**Upgrading:**
|
|
@@ -162,7 +164,7 @@ The next major release sunsets the Bash runtime entirely. There is no firm calen
|
|
|
162
164
|
| Method | Command |
|
|
163
165
|
|--------|---------|
|
|
164
166
|
| **Homebrew** | `brew tap asklokesh/tap && brew install loki-mode` |
|
|
165
|
-
| **Docker** | `docker pull asklokesh/loki-mode:7.
|
|
167
|
+
| **Docker** | `docker pull asklokesh/loki-mode:7.31.0` |
|
|
166
168
|
| **Inside Claude Code** | `claude --dangerously-skip-permissions` then type "Loki Mode" |
|
|
167
169
|
| **Git clone** | `git clone https://github.com/asklokesh/loki-mode.git` |
|
|
168
170
|
|
package/SKILL.md
CHANGED
|
@@ -3,7 +3,7 @@ name: loki-mode
|
|
|
3
3
|
description: Autonomous spec-driven build system with a built-in trust layer. It does not call work done until it is verified (RARV-C closure loop, 11 quality gates, completion council, verified-completion evidence gate). Triggers on "Loki Mode". Takes a spec (PRD, GitHub issue, OpenAPI doc, etc.) to deployed product with minimal human intervention. Provider-agnostic. Requires --dangerously-skip-permissions flag.
|
|
4
4
|
---
|
|
5
5
|
|
|
6
|
-
# Loki Mode v7.
|
|
6
|
+
# Loki Mode v7.31.0
|
|
7
7
|
|
|
8
8
|
**You are an autonomous agent. You make decisions. You do not ask questions. You do not stop.**
|
|
9
9
|
|
|
@@ -398,4 +398,4 @@ See `CHANGELOG.md` entries [7.5.7], [7.5.8], [7.5.13] for the per-fix list and r
|
|
|
398
398
|
|
|
399
399
|
---
|
|
400
400
|
|
|
401
|
-
**v7.
|
|
401
|
+
**v7.31.0 | [Autonomi](https://www.autonomi.dev/) flagship product | ~260 lines core**
|
package/VERSION
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
7.
|
|
1
|
+
7.31.0
|
|
@@ -28,6 +28,14 @@ from pathlib import Path
|
|
|
28
28
|
|
|
29
29
|
|
|
30
30
|
# Default pricing (USD per million tokens) - provider-specific overrides below
|
|
31
|
+
# NOTE (fable): this table is keyed by PROVIDER (claude/codex/gemini), not by
|
|
32
|
+
# model, so it cannot price Fable distinctly from Opus/Sonnet under "claude".
|
|
33
|
+
# It is intentionally NOT refactored for the fable change: this table is an
|
|
34
|
+
# ESTIMATE-ONLY fallback for context-window projections. The authoritative
|
|
35
|
+
# per-run spend is captured from Claude's real total_cost_usd (v7.28.0 result-cost
|
|
36
|
+
# capture) and the model-keyed tables in run.sh / dashboard/server.py, which DO
|
|
37
|
+
# carry a fable row at $10/$50. So real Fable spend is priced correctly regardless
|
|
38
|
+
# of this provider-keyed fallback.
|
|
31
39
|
PRICING_BY_PROVIDER = {
|
|
32
40
|
"claude": {
|
|
33
41
|
"input": 3.0,
|