loki-mode 6.4.0 → 6.6.0

package/README.md

@@ -9,7 +9,7 @@
 [![Agent Types](https://img.shields.io/badge/Agent%20Types-41-blue)]()
 [![Autonomi](https://img.shields.io/badge/Autonomi-autonomi.dev-5B4EEA)](https://www.autonomi.dev/)
 
-**Current Version: v6.2.1**
+**Current Version: v6.6.0**
 
 ---
 
@@ -36,7 +36,7 @@ Every iteration follows the **RARV cycle**: Reason (read state, identify next ta
 | **Code Generation** | Full-stack apps from PRDs | Complex domain logic may need human review |
 | **Deployment** | Generates configs, Dockerfiles, CI/CD workflows | Does not deploy -- human provides cloud credentials and runs deploy |
 | **Testing** | 9 automated quality gates, blind review | Test quality depends on AI-generated assertions |
-| **Multi-Provider** | Claude (full), Codex/Gemini (sequential only) | Codex and Gemini lack parallel agents and Task tool |
+| **Multi-Provider** | Claude (full), Codex/Gemini/Cline/Aider (sequential only) | Non-Claude providers lack parallel agents and Task tool |
 | **Enterprise** | TLS, OIDC, RBAC, audit trail | Self-signed certs only; some features require env var activation |
 | **Dashboard** | Real-time status, task queue, agents | Single-machine only; no multi-node clustering |
 
@@ -44,7 +44,7 @@ Every iteration follows the **RARV cycle**: Reason (read state, identify next ta
 
 ## Quick Start
 
-**Requirements:** Node.js 18+, Python 3.8+, macOS/Linux/WSL2, and at least one AI CLI (Claude Code, Codex, or Gemini).
+**Requirements:** Node.js 18+, Python 3.8+, macOS/Linux/WSL2, and at least one AI CLI (Claude Code, Codex, Gemini, Cline, or Aider).
 
 ### CLI Mode
 
@@ -129,7 +129,7 @@ See [full architecture documentation](docs/enterprise/architecture.md) for the d
 | **Quality** | 9 gates: blind review, anti-sycophancy, mock/mutation detection | [Quality Gates](skills/quality-gates.md) |
 | **Dashboard** | Real-time monitoring, API v2, WebSocket, auto-starts with `loki start` | [Dashboard Guide](docs/dashboard-guide.md) |
 | **Memory** | 3-tier (episodic/semantic/procedural), knowledge graph, vector search | [Memory System](references/memory-system.md) |
-| **Providers** | Claude (full), Codex (sequential), Gemini (sequential) | [Provider Guide](skills/providers.md) |
+| **Providers** | Claude (full), Codex/Gemini/Cline/Aider (sequential) | [Provider Guide](skills/providers.md) |
 | **Enterprise** | TLS, OIDC/SSO, RBAC, OTEL, policy engine, audit trails | [Enterprise Guide](docs/enterprise/architecture.md) |
 | **Integrations** | Jira, Slack, Teams, GitHub Actions (Linear: partial) | [Integration Cookbook](docs/enterprise/integration-cookbook.md) |
 | **Deployment** | Helm, Docker Compose, Terraform configs (AWS/Azure/GCP) | [Deployment Guide](deploy/helm/README.md) |
@@ -142,8 +142,10 @@ See [full architecture documentation](docs/enterprise/architecture.md) for the d
 | Claude Code | `npm i -g @anthropic-ai/claude-code` | `--dangerously-skip-permissions` | Yes (10+) |
 | Codex CLI | `npm i -g @openai/codex` | `--full-auto` | No (sequential) |
 | Gemini CLI | `npm i -g @google/gemini-cli` | `--approval-mode=yolo` | No (sequential) |
+| Cline CLI | `npm i -g @anthropic-ai/cline` | `--auto-approve` | No (sequential) |
+| Aider | `pip install aider-chat` | `--yes-always` | No (sequential) |
 
-Claude gets full features (subagents, parallelization, MCP, Task tool). Codex and Gemini run in sequential mode -- one agent at a time, no Task tool. See [Provider Guide](skills/providers.md) for the full comparison.
+Claude gets full features (subagents, parallelization, MCP, Task tool). All other providers run in sequential mode -- one agent at a time, no Task tool. See [Provider Guide](skills/providers.md) for the full comparison.
 
 ---
 

package/SKILL.md

@@ -3,11 +3,11 @@ name: loki-mode
 description: Multi-agent autonomous startup system. Triggers on "Loki Mode". Takes PRD to deployed product with minimal human intervention. Requires --dangerously-skip-permissions flag.
 ---
 
-# Loki Mode v6.4.0
+# Loki Mode v6.6.0
 
 **You are an autonomous agent. You make decisions. You do not ask questions. You do not stop.**
 
-**New in v5.0.0:** Multi-provider support (Claude/Codex/Gemini), abstract model tiers, degraded mode for non-Claude providers. See `skills/providers.md`.
+**New in v5.0.0:** Multi-provider support (Claude/Codex/Gemini/Cline/Aider), abstract model tiers, degraded mode for non-Claude providers. See `skills/providers.md`.
 
 ---
 
@@ -95,7 +95,7 @@ These rules guide autonomous operation. Test results and code quality always tak
 
 **Parallelization rule (Claude only):** Launch up to 10 agents simultaneously for independent tasks.
 
-**Degraded mode (Codex/Gemini):** No parallel agents or Task tool. Codex has MCP support. Runs RARV cycle sequentially. See `skills/model-selection.md`.
+**Degraded mode (Codex/Gemini/Cline/Aider):** No parallel agents or Task tool. Codex has MCP support. Runs RARV cycle sequentially. See `skills/model-selection.md`.
 
 **Git worktree parallelism:** For true parallel feature development, use `--parallel` flag with run.sh. See `skills/parallel-workflows.md`.
 
@@ -187,6 +187,8 @@ claude --dangerously-skip-permissions
 ./autonomy/run.sh --provider claude ./prd.md   # Default, full features
 ./autonomy/run.sh --provider codex ./prd.json  # GPT-5.3 Codex, degraded mode
 ./autonomy/run.sh --provider gemini ./prd.md   # Gemini 3 Pro, degraded mode
+./autonomy/run.sh --provider cline ./prd.md    # Cline CLI, degraded mode
+./autonomy/run.sh --provider aider ./prd.md    # Aider (18+ providers), degraded mode
 
 # Or via CLI wrapper
 loki start --provider codex ./prd.md
@@ -199,6 +201,8 @@ loki start --provider codex ./prd.md
 - **Claude**: Opus 4.6, 1M context (beta), 128K output, adaptive thinking, agent teams, full features (Task tool, parallel agents, MCP)
 - **Codex**: GPT-5.3, 400K context, 128K output, MCP support, --full-auto mode, degraded (sequential only, no Task tool)
 - **Gemini**: Degraded mode (sequential only, no Task tool, 1M context)
+- **Cline**: Multi-provider CLI, degraded mode (sequential only, no Task tool)
+- **Aider**: 18+ provider backends, degraded mode (sequential only, no Task tool)
 
 ---
 
@@ -263,4 +267,4 @@ The following features are documented in skill modules but not yet fully automat
 | Quality gates 3-reviewer system | Implemented (v5.35.0) | 5 specialist reviewers in `skills/quality-gates.md`; execution in run.sh |
 | Benchmarks (HumanEval, SWE-bench) | Infrastructure only | Runner scripts and datasets exist in `benchmarks/`; no published results |
 
-**v6.4.0 | [Autonomi](https://www.autonomi.dev/) flagship product | ~260 lines core**
+**v6.6.0 | [Autonomi](https://www.autonomi.dev/) flagship product | ~260 lines core**

package/VERSION

@@ -1 +1 @@
-6.4.0
+6.6.0

package/autonomy/completion-council.sh

@@ -663,6 +663,8 @@ council_member_review() {
         claude) command -v claude >/dev/null 2>&1 || { log_error "Claude CLI not found"; return 1; } ;;
         codex) command -v codex >/dev/null 2>&1 || { log_error "Codex CLI not found"; return 1; } ;;
         gemini) command -v gemini >/dev/null 2>&1 || { log_error "Gemini CLI not found"; return 1; } ;;
+        cline) command -v cline >/dev/null 2>&1 || { log_error "Cline CLI not found"; return 1; } ;;
+        aider) command -v aider >/dev/null 2>&1 || { log_error "Aider not found"; return 1; } ;;
     esac
 
     local evidence
@@ -753,6 +755,16 @@ ISSUES: CRITICAL:description (optional, one per line per issue)"
                 verdict=$(echo "$prompt" | gemini 2>/dev/null | tail -5)
             fi
             ;;
+        cline)
+            if command -v cline &>/dev/null; then
+                verdict=$(cline -y "$prompt" 2>/dev/null | tail -5)
+            fi
+            ;;
+        aider)
+            if command -v aider &>/dev/null; then
+                verdict=$(aider --message "$prompt" --yes-always --no-auto-commits --no-git 2>/dev/null | tail -5)
+            fi
+            ;;
     esac
 
     # Fallback: if no AI provider available, use heuristic-based review
@@ -777,6 +789,8 @@ council_devils_advocate() {
         claude) command -v claude >/dev/null 2>&1 || { log_error "Claude CLI not found"; return 1; } ;;
         codex) command -v codex >/dev/null 2>&1 || { log_error "Codex CLI not found"; return 1; } ;;
         gemini) command -v gemini >/dev/null 2>&1 || { log_error "Gemini CLI not found"; return 1; } ;;
+        cline) command -v cline >/dev/null 2>&1 || { log_error "Cline CLI not found"; return 1; } ;;
+        aider) command -v aider >/dev/null 2>&1 || { log_error "Aider not found"; return 1; } ;;
     esac
 
     local evidence
@@ -830,6 +844,16 @@ REASON: your reasoning"
                 verdict=$(echo "$prompt" | gemini 2>/dev/null | tail -5)
             fi
             ;;
+        cline)
+            if command -v cline &>/dev/null; then
+                verdict=$(cline -y "$prompt" 2>/dev/null | tail -5)
+            fi
+            ;;
+        aider)
+            if command -v aider &>/dev/null; then
+                verdict=$(aider --message "$prompt" --yes-always --no-auto-commits --no-git 2>/dev/null | tail -5)
+            fi
+            ;;
     esac
 
     if [ -z "$verdict" ]; then

package/autonomy/council-v2.sh

@@ -282,6 +282,20 @@ Respond ONLY with a valid JSON object. No markdown fencing."
                 result='{"verdict":"REJECT","reasoning":"reviewer CLI unavailable","issues":[]}'
             fi
             ;;
+        cline)
+            if command -v cline &>/dev/null; then
+                result=$(cline -y "$full_prompt" 2>/dev/null || echo '{"verdict":"REJECT","reasoning":"review execution failed","issues":[]}')
+            else
+                result='{"verdict":"REJECT","reasoning":"reviewer CLI unavailable","issues":[]}'
+            fi
+            ;;
+        aider)
+            if command -v aider &>/dev/null; then
+                result=$(aider --message "$full_prompt" --yes-always --no-auto-commits --no-git 2>/dev/null || echo '{"verdict":"REJECT","reasoning":"review execution failed","issues":[]}')
+            else
+                result='{"verdict":"REJECT","reasoning":"reviewer CLI unavailable","issues":[]}'
+            fi
+            ;;
         *)
             result='{"verdict":"REJECT","reasoning":"review not supported for this provider","issues":[]}'
             ;;

package/autonomy/hooks/migration-hooks.sh

@@ -52,7 +52,7 @@ load_migration_hook_config() {
         # Parse YAML config safely using read/declare instead of eval
         while IFS='=' read -r key val; do
             case "$key" in
-                HOOK_*) declare -g "$key=$val" ;;
+                HOOK_*) printf -v "$key" '%s' "$val" ;;
             esac
         done < <(python3 -c "
 import sys
@@ -224,7 +224,7 @@ try:
     print(len([s for s in steps if s.get('status') != 'completed']))
 except: print(-1)
 " 2>/dev/null || echo -1)
-            [[ "$pending" -gt 0 ]] && echo "GATE_BLOCKED: ${pending} steps still pending" && return 1
+            [[ "$pending" -ne 0 ]] && echo "GATE_BLOCKED: ${pending} steps still pending (or plan missing)" && return 1
             ;;
     esac
 
@@ -236,6 +236,10 @@ hook_on_agent_stop() {
     local features_path="${LOKI_FEATURES_PATH:-}"
 
     [[ "$HOOK_ON_AGENT_STOP_ENABLED" != "true" ]] && return 0
+    if [[ -z "$features_path" ]]; then
+        echo "HOOK_BLOCKED: LOKI_FEATURES_PATH not set. Cannot verify features."
+        return 1
+    fi
     [[ ! -f "$features_path" ]] && return 0
 
     local failing