indusagi-coding-agent 0.1.43 → 0.1.44

package/guides/{PI_MONO_MIT_REMOVAL_GUIDE.md → INDUSAGI_MONO_MIT_REMOVAL_GUIDE.md}

@@ -1,8 +1,8 @@
-# PI Mono MIT Removal Guide for `indusagi-screth`
+# Indusagi Mono MIT Removal Guide for `indusagi-screth`
 
 
 
-> **Important:** This is a technical provenance-cleanup guide, **not legal advice**. If you want to make a strong public claim like _"`indusagi-screth` contains no PI Mono derived code"_, you should still do a final legal/provenance review.
+> **Important:** This is a technical provenance-cleanup guide, **not legal advice**. If you want to make a strong public claim like _"`indusagi-screth` contains no Indusagi Mono derived code"_, you should still do a final legal/provenance review.
 
 
 
@@ -10,21 +10,21 @@
 
 
 
-If the goal is to make `indusagi-screth` **PI Mono MIT-free**, the safe standard is:ß
+If the goal is to make `indusagi-screth` **Indusagi Mono MIT-free**, the safe standard is:ß
 
 
 
-1. No copied PI Mono source files remain.
+1. No copied Indusagi Mono source files remain.
 
-2. No adapted/derived PI Mono files remain unless you are willing to keep MIT attribution.
+2. No adapted/derived Indusagi Mono files remain unless you are willing to keep MIT attribution.
 
 3. Third-party vendor assets are either:
 
    - replaced by direct upstream package installation/build steps, or
 
-   - kept with their own proper attribution, independent of PI Mono.
+   - kept with their own proper attribution, independent of Indusagi Mono.
 
-4. Documentation, package metadata, and marketing text do not imply PI Mono-derived implementation if that is no longer true.
+4. Documentation, package metadata, and marketing text do not imply Indusagi Mono-derived implementation if that is no longer true.
 
 
 
@@ -34,7 +34,7 @@ If the goal is to make `indusagi-screth` **PI Mono MIT-free**, the safe standard
 
 Compared repos:
 
-- `@pi-mono/packages/coding-agent/`
+- `@indusagi-mono/packages/coding-agent/`
 
 - `@indusagi-screth/`
 
@@ -50,7 +50,7 @@ Current overlap snapshot:
 
 
 
-That means `indusagi-screth` is **not** currently in a position where it is safe to say _"PI Mono copyright does not apply"_. There is still enough exact and likely-derived overlap that a cleanup pass is required.
+That means `indusagi-screth` is **not** currently in a position where it is safe to say _"Indusagi Mono copyright does not apply"_. There is still enough exact and likely-derived overlap that a cleanup pass is required.
 
 
 
@@ -70,7 +70,7 @@ Before rewriting anything, follow these rules:
 
 
 
-- Do **not** use PI Mono files as copy-paste sources during the rewrite.
+- Do **not** use Indusagi Mono files as copy-paste sources during the rewrite.
 
 - Rewrite from behavior/specification, not from line-by-line adaptation.
 
@@ -82,7 +82,7 @@ Before rewriting anything, follow these rules:
 
   - `kept and MIT attribution retained`
 
-- If a file is still PI Mono-derived after cleanup, keep MIT attribution for that file/subtree.
+- If a file is still Indusagi Mono-derived after cleanup, keep MIT attribution for that file/subtree.
 
 
 
@@ -94,7 +94,7 @@ Before rewriting anything, follow these rules:
 
 
 
-These are the highest-risk files because they currently match PI Mono exactly.
+These are the highest-risk files because they currently match Indusagi Mono exactly.
 
 
 
@@ -118,7 +118,7 @@ These are the highest-risk files because they currently match PI Mono exactly.
 
 ### P1-B. Exact vendor / asset files to replace properly
 
-These should not stay as copied repo assets if the goal is "PI Mono MIT-free provenance".
+These should not stay as copied repo assets if the goal is "Indusagi Mono MIT-free provenance".
 
 
 
@@ -136,7 +136,7 @@ For each file above, do one of:
 
 - full independent rewrite, or
 
-- replace from original upstream package/source with proper direct attribution, not via PI Mono copy.
+- replace from original upstream package/source with proper direct attribution, not via Indusagi Mono copy.
 
 ### P1 status update
 
@@ -308,7 +308,7 @@ These should **not** be hand-edited.
 - new control-flow shape
 - new intermediate data model
 - same behavior implemented through a different code path
-- vendor assets replaced from direct upstream instead of PI Mono copies
+- vendor assets replaced from direct upstream instead of Indusagi Mono copies
 
 
 
@@ -410,7 +410,7 @@ These files are not byte-identical, but they share the same path and likely shar
 
 ### Why P2 is critical
 
-If these remain structurally PI Mono-derived, then even rewriting surface docs or utilities will not materially change provenance risk.
+If these remain structurally Indusagi Mono-derived, then even rewriting surface docs or utilities will not materially change provenance risk.
 
 ### Focused P2 plan for the currently requested files
 
@@ -418,7 +418,7 @@ If these remain structurally PI Mono-derived, then even rewriting surface docs o
 
 ### Focused P2 post-rewrite recheck (approximate)
 
-**Method note:** the percentages below are an approximate **post-P2** recheck against `@pi-mono/packages/coding-agent/`, using a `git diff --no-index --word-diff=porcelain` unchanged-text ratio. These numbers are meant for provenance prioritization, not as a legal or plagiarism determination.
+**Method note:** the percentages below are an approximate **post-P2** recheck against `@indusagi-mono/packages/coding-agent/`, using a `git diff --no-index --word-diff=porcelain` unchanged-text ratio. These numbers are meant for provenance prioritization, not as a legal or plagiarism determination.
 
 | File | Post-P2 similarity | Post-P2 difference |
 |---|---:|---:|
@@ -440,7 +440,7 @@ If these remain structurally PI Mono-derived, then even rewriting surface docs o
 
 ### Focused P2 post-rewrite takeaway
 
-This recheck suggests the biggest previously high-similarity P2 files have moved materially away from PI Mono structure in this batch. In particular:
+This recheck suggests the biggest previously high-similarity P2 files have moved materially away from Indusagi Mono structure in this batch. In particular:
 
 - `src/core/prompt-templates.ts` moved from the earlier near-match risk zone to `30.9%` similarity / `69.1%` difference.
 - `src/core/session-manager.ts` moved from the earlier near-match risk zone to `15.2%` similarity / `84.8%` difference.
@@ -495,7 +495,7 @@ The files you called out are spread across bootstrap, CLI parsing, runtime orche
 
 **Minimal but meaningful rewrite:**
 - move MCP log suppression into named helper(s)
-- avoid top-level anonymous patch structure copied from PI Mono style
+- avoid top-level anonymous patch structure copied from Indusagi Mono style
 - introduce a `bootstrapCli()` wrapper that owns process-title + logger patch + main invocation
 
 **Suggested rewrite shape:**
@@ -526,7 +526,7 @@ The files you called out are spread across bootstrap, CLI parsing, runtime orche
 - separate package-root detection from exported path helpers
 - centralize env var resolution and tilde expansion
 - group asset path helpers vs user config path helpers vs metadata exports
-- reduce structural resemblance to current PI Mono layout even if behavior stays the same
+- reduce structural resemblance to current Indusagi Mono layout even if behavior stays the same
 
 **Suggested rewrite shape:**
 - `resolvePackageRoot()`
@@ -1050,7 +1050,7 @@ Validation after the P3 rewrite pass:
 
 ### Focused P3 post-rewrite recheck (approximate)
 
-**Method note:** the percentages below are an approximate **post-P3** recheck against `@pi-mono/packages/coding-agent/`, using a `git diff --no-index --word-diff=porcelain` unchanged-text ratio. These numbers are meant for provenance prioritization, not as a legal or plagiarism determination.
+**Method note:** the percentages below are an approximate **post-P3** recheck against `@indusagi-mono/packages/coding-agent/`, using a `git diff --no-index --word-diff=porcelain` unchanged-text ratio. These numbers are meant for provenance prioritization, not as a legal or plagiarism determination.
 
 | File | Post-P3 similarity | Post-P3 difference |
 |---|---:|---:|
@@ -1097,7 +1097,7 @@ So unlike the focused P2 batch, the focused P3 batch is **not yet all below `40%
 
 
 
-These files are many, but they are important because the TUI layer is highly expressive and likely to preserve PI Mono structure even after edits. Rewrite after P2/P3.
+These files are many, but they are important because the TUI layer is highly expressive and likely to preserve Indusagi Mono structure even after edits. Rewrite after P2/P3.
 
 
 
@@ -1680,7 +1680,7 @@ That materially changes the repository-wide overlap picture: there are no longer
 
 
 
-These files exist in `indusagi-screth` but not in PI Mono, so they are **not immediate PI Mono overlap evidence** based on path comparison alone:
+These files exist in `indusagi-screth` but not in Indusagi Mono, so they are **not immediate Indusagi Mono overlap evidence** based on path comparison alone:
 
 
 
@@ -1716,7 +1716,7 @@ These files exist in `indusagi-screth` but not in PI Mono, so they are **not imm
 
 
 
-These still deserve provenance review, but they are **not first priority** for PI Mono separation.
+These still deserve provenance review, but they are **not first priority** for Indusagi Mono separation.
 
 
 
@@ -1756,7 +1756,7 @@ These still deserve provenance review, but they are **not first priority** for P
 
 ## Phase 4 — Final cleanup
 
-8. Re-run repo comparison against PI Mono.
+8. Re-run repo comparison against Indusagi Mono.
 
 9. Confirm there are no exact-match code files left.
 
@@ -1774,13 +1774,13 @@ These still deserve provenance review, but they are **not first priority** for P
 
 
 
-You can make a much stronger statement like _"`indusagi-screth` is no longer PI Mono-derived"_ only when all of the following are true:
+You can make a much stronger statement like _"`indusagi-screth` is no longer Indusagi Mono-derived"_ only when all of the following are true:
 
 
 
-- [ ] No exact identical PI Mono code files remain.
+- [ ] No exact identical Indusagi Mono code files remain.
 
-- [ ] No copied PI Mono vendor assets remain unless separately sourced and attributed.
+- [ ] No copied Indusagi Mono vendor assets remain unless separately sourced and attributed.
 
 - [ ] High-risk core files have been independently rewritten.
 
@@ -1858,7 +1858,7 @@ These percentages are **approximate line-based estimates**, not legal determinat
 
 Method used:
 
-- compare the PI Mono file and the `indusagi-screth` file at the same relative path
+- compare the Indusagi Mono file and the `indusagi-screth` file at the same relative path
 
 - use line counts plus `git diff --no-index --numstat` style added/deleted line counts
 

package/guides/OPTION3_PROVIDER_ADAPTER_RUNTIME_PLAN.md

@@ -0,0 +1,370 @@
+# Option 3 Plan: Full Provider Adapter Runtime (Claude CLI / Codex CLI / Indusagi CLI)
+
+## Objective
+
+Implement a **production-grade provider runtime layer** in `indusagi-screth` so CLI-backed providers behave as first-class runtimes, not just `streamSimple` wrappers.
+
+Target providers:
+
+- `claude-cli`
+- `codex-cli`
+- `indusagi-cli`
+
+---
+
+## Success Criteria
+
+1. Selecting any of the 3 providers routes execution through a dedicated adapter runtime.
+2. Session lifecycle is explicit: start, send turn, interrupt, shutdown, recover.
+3. Provider events are normalized into the existing `AssistantMessageEventStream` path.
+4. Session state persists enough metadata to resume reliably.
+5. Existing API providers keep working unchanged.
+
+---
+
+## Current Constraints in Codebase
+
+Relevant current flow:
+
+- Provider registration and model list:
+  - `app/runtime/model-registry.ts`
+- Stream execution path:
+  - `app/runtime/sdk.ts` (`createStreamWithHooks` -> `streamSimple(...)`)
+- Session orchestration and persistence:
+  - `app/runtime/agent-session.ts`
+  - `app/runtime/session-manager.ts`
+- Extension registration queue:
+  - `app/runtime/plugins/loader.ts`
+  - `app/runtime/plugins/runner.ts`
+  - `app/main.ts`
+- Existing RPC client (useful for `indusagi-cli` adapter):
+  - `app/interfaces/service-api/rpc-client.ts`
+
+Problem: current runtime assumes model API adapters. CLI runtimes require their own session/event lifecycle.
+
+---
+
+## Target Architecture
+
+## 1) New Provider Runtime Module
+
+Create a new module tree:
+
+- `app/runtime/providers/types.ts`
+- `app/runtime/providers/provider-adapter.ts`
+- `app/runtime/providers/provider-adapter-registry.ts`
+- `app/runtime/providers/provider-service.ts`
+- `app/runtime/providers/adapters/claude-cli-adapter.ts`
+- `app/runtime/providers/adapters/codex-cli-adapter.ts`
+- `app/runtime/providers/adapters/indusagi-cli-adapter.ts`
+
+## 2) Core Interfaces
+
+### `ProviderAdapter`
+
+```ts
+export interface ProviderAdapter {
+  readonly id: string;
+  supports(provider: string): boolean;
+
+  startSession(input: {
+    provider: string;
+    modelId: string;
+    sessionId: string;
+    cwd: string;
+  }): Promise<ProviderSessionHandle>;
+
+  streamTurn(input: {
+    handle: ProviderSessionHandle;
+    model: Model<Api>;
+    context: Context;
+    options?: SimpleStreamOptions;
+  }): AssistantMessageEventStream;
+
+  interrupt(handle: ProviderSessionHandle): Promise<void>;
+  stopSession(handle: ProviderSessionHandle): Promise<void>;
+  healthCheck?(): Promise<{ ok: boolean; reason?: string }>;
+}
+```
+
+### `ProviderSessionHandle`
+
+Contains adapter-managed runtime identity and metadata:
+
+- `adapterId`
+- `provider`
+- `modelId`
+- `runtimeSessionId` (thread/conversation/process id)
+- adapter-specific opaque payload
+
+## 3) `ProviderService`
+
+Responsibilities:
+
+- decide whether a model/provider should use adapter runtime
+- get or create adapter session handle for current agent session
+- stream one turn via adapter
+- interrupt/cleanup active runtime
+- persist runtime metadata for restore
+
+Internal state map:
+
+- `Map<agentSessionId, ProviderSessionHandle>`
+
+## 4) Adapter Registry
+
+Responsibilities:
+
+- register adapters
+- resolve by provider id
+- expose diagnostics for availability checks
+
+---
+
+## Integration Plan (File-Level)
+
+## Phase 0 — Scaffolding
+
+### Add new files
+
+- `app/runtime/providers/types.ts`
+- `app/runtime/providers/provider-adapter.ts`
+- `app/runtime/providers/provider-adapter-registry.ts`
+- `app/runtime/providers/provider-service.ts`
+
+### Add lightweight tests
+
+- `tests/runtime/providers/provider-adapter-registry.test.ts`
+- `tests/runtime/providers/provider-service.test.ts`
+
+---
+
+## Phase 1 — Runtime Routing in SDK
+
+### Modify `app/runtime/sdk.ts`
+
+1. Create `ProviderAdapterRegistry` during `createAgentSession()` bootstrap.
+2. Register built-in adapters (`claude-cli`, `codex-cli`, `indusagi-cli`).
+3. Create `ProviderService` and inject references:
+   - session id from `SessionManager`
+   - cwd
+4. Update `createStreamWithHooks(...)`:
+   - before `streamSimple(...)`, call provider service:
+     - if adapter exists for `model.provider`, use `providerService.streamTurn(...)`
+     - else fallback to existing `streamSimple(...)`
+
+Result: model/API providers unaffected; only targeted CLI providers reroute.
+
+---
+
+## Phase 2 — Provider Metadata + Validation
+
+### Modify `app/runtime/model-registry.ts`
+
+Add provider runtime metadata support in `ProviderConfigInput`:
+
+```ts
+runtime?: {
+  adapter: "claude-cli" | "codex-cli" | "indusagi-cli" | string;
+  authMode?: "apiKey" | "oauth" | "external-cli" | "none";
+}
+```
+
+Changes:
+
+1. Persist runtime config per provider in registry map.
+2. Add `getProviderRuntime(provider: string)` accessor.
+3. Relax validation for `models` when runtime auth is external:
+   - if `runtime.authMode` is `external-cli` or `none`, do not require `apiKey/oauth`.
+4. Keep existing validation for normal HTTP API providers.
+
+### Modify extension type surface
+
+- `app/runtime/plugins/types.ts`
+  - extend `ProviderConfig` with same `runtime` field.
+
+---
+
+## Phase 3 — Session Persistence for Adapter State
+
+### Modify `app/runtime/session-manager.ts`
+
+Use existing custom entry mechanism:
+
+- `appendCustomEntry("provider_runtime", data)`
+
+Persist after adapter session creation/update:
+
+```json
+{
+  "type": "custom",
+  "customType": "provider_runtime",
+  "data": {
+    "provider": "codex-cli",
+    "adapterId": "codex-cli",
+    "modelId": "gpt-5.4-1m",
+    "runtimeSessionId": "...",
+    "timestamp": "..."
+  }
+}
+```
+
+On startup, `ProviderService` should inspect latest relevant custom entry and attempt restore.
+
+---
+
+## Phase 4 — Adapter Implementations
+
+## 4.1 `IndusagiCliAdapter` (first, easiest)
+
+File:
+
+- `app/runtime/providers/adapters/indusagi-cli-adapter.ts`
+
+Implementation:
+
+- use existing `RpcClient` (`app/interfaces/service-api/rpc-client.ts`)
+- start subprocess in `--mode rpc`
+- set provider/model if needed
+- map incoming RPC events to `AssistantMessageEventStream` events
+- support interrupt/stop cleanly
+
+Why first: strong existing API and event stream already available.
+
+## 4.2 `CodexCliAdapter`
+
+File:
+
+- `app/runtime/providers/adapters/codex-cli-adapter.ts`
+
+Implementation approach:
+
+- mimic t3code `codex app-server` management pattern
+- manage process lifecycle per agent session
+- translate codex events -> normalized assistant stream
+- implement robust retry and “binary missing” errors
+
+## 4.3 `ClaudeCliAdapter`
+
+File:
+
+- `app/runtime/providers/adapters/claude-cli-adapter.ts`
+
+Implementation approach:
+
+- support preferred Claude CLI invocation/session mode available in your environment
+- parse streaming/stdout events to text deltas
+- add cancellation + process cleanup
+
+---
+
+## Phase 5 — Agent Session Hooks
+
+### Modify `app/runtime/agent-session.ts`
+
+Add lifecycle hooks to call provider service:
+
+1. On model change to non-adapter provider:
+   - stop old adapter session handle (if exists).
+2. On user interrupt/steer path:
+   - call `providerService.interrupt(...)` when current provider is adapter-backed.
+3. On session shutdown:
+   - `providerService.stopSession(...)`.
+
+Goal: no orphan subprocesses and predictable cancellation.
+
+---
+
+## Phase 6 — CLI UX and Login Surface
+
+### Modify `app/command-line/login-handler.ts`
+
+- include adapter providers only if they actually support login.
+- for `external-cli` auth mode, show clear message:
+  - “Authenticate using provider CLI command (e.g., `claude login`, `codex login`)”
+
+### Modify `app/command-line/list-models.ts` (optional enhancement)
+
+- show runtime-backed providers even without API keys when `authMode=external-cli` and health check passes.
+
+---
+
+## Phase 7 — Tests
+
+Add tests in:
+
+- `tests/runtime/providers/*.test.ts`
+- `tests/runtime/model-registry*.test.ts`
+- `tests/runtime/sdk*.test.ts`
+
+### Required coverage
+
+1. Routing: adapter provider uses `ProviderService`, others use `streamSimple`.
+2. Validation: runtime external providers do not require apiKey/oauth.
+3. Persistence: provider runtime custom entry is written and restored.
+4. Interrupt/shutdown: child process cleanup runs.
+5. Error handling: binary missing, startup failure, malformed stream.
+
+---
+
+## Phase 8 — Rollout Strategy
+
+1. Ship behind env flag:
+   - `INDUSAGI_ENABLE_PROVIDER_ADAPTERS=1`
+2. Enable only `indusagi-cli` adapter first.
+3. Then enable `codex-cli` and `claude-cli` after integration tests pass.
+4. Remove flag when stable.
+
+---
+
+## Event Normalization Rules
+
+All adapters must normalize to one contract:
+
+1. `pushStart(output)`
+2. `pushTextStart(index, output)` once
+3. `pushTextDelta(index, delta, output)` many times
+4. `pushTextEnd(index, finalText, output)` once
+5. `pushDone(stopReason, output)` once
+6. `pushError(...)` on failure path
+
+Non-text native events (approvals/tool telemetry) should be mapped to session custom entries first, then surfaced in UI incrementally.
+
+---
+
+## Risks and Mitigations
+
+1. **Provider protocol drift** (CLI output formats change)
+   - Mitigation: adapter-level parsers with golden tests.
+
+2. **Process leaks**
+   - Mitigation: strict stop/timeout/SIGKILL policy in provider service.
+
+3. **Auth ambiguity for external CLI**
+   - Mitigation: explicit `authMode=external-cli` + health checks + clear UX copy.
+
+4. **Session mismatch on restore**
+   - Mitigation: store adapter/model/provider in custom entry and validate before restore.
+
+---
+
+## Definition of Done
+
+- [ ] New provider runtime module exists with registry/service/adapters.
+- [ ] `sdk.ts` routes adapter providers through provider service.
+- [ ] `model-registry.ts` supports runtime metadata and external-cli auth mode.
+- [ ] Adapter session metadata persisted and restorable.
+- [ ] `indusagi-cli` adapter fully working via RPC.
+- [ ] `codex-cli` and `claude-cli` adapters pass smoke tests.
+- [ ] No regressions for existing API providers.
+
+---
+
+## Recommended Execution Order (Practical)
+
+1. Build shared runtime module + routing.
+2. Implement `indusagi-cli` adapter first (uses existing RPC client).
+3. Add persistence + interruption handling.
+4. Implement `codex-cli` adapter.
+5. Implement `claude-cli` adapter.
+6. Harden tests and remove feature flag.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "indusagi-coding-agent",
-  "version": "0.1.43",
+  "version": "0.1.44",
   "description": "Terminal-first TypeScript coding agent built on the published indusagi package.",
   "type": "module",
   "main": "./dist/index.js",
@@ -34,7 +34,7 @@
     "sync:export-vendors": "node tasks/sync-export-vendors.mjs",
     "copy:export-assets": "node tasks/copy-export-assets.mjs",
     "build": "npm run build:observe-local && npm run sync:export-vendors && tsc -p tsconfig.build.json && npm run copy:export-assets && shx chmod +x dist/cli.js",
-    "build:observe-local": "node -e \"console.log('Using published indusagi@0.12.23')\"",
+    "build:observe-local": "node -e \"console.log('Using published indusagi@0.12.24')\"",
     "observe:smoke": "npm run build && node dist/dev/observe-smoke.js",
     "observe:smoke:serve": "npm run build && node dist/dev/observe-smoke.js --serve",
     "observe:deep": "npm run build && node dist/dev/observe-deep.js",
@@ -53,7 +53,7 @@
     "glob": "^11.0.3",
     "highlight.js": "^11.11.1",
     "i": "^0.3.7",
-    "indusagi": "^0.12.23",
+    "indusagi": "^0.12.24",
     "indusagi-coding-agent": "^0.1.42",
     "marked": "^17.0.5",
     "minimatch": "^10.0.3",