askii-cli 0.2.12 → 0.3.0

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.
Files changed (3) hide show
  1. package/README.md +77 -44
  2. package/dist/index.js +235 -228
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # ASKII CLI ( •\_•)>⌐■-■ (⌐■_■)
2
2
 
3
- AI code assistant for your terminal. Powered by Ollama, LM Studio, OpenAI, or Anthropic.
3
+ AI code assistant for your terminal. Powered by Ollama, LM Studio, OpenAI, Anthropic, or opencode Go.
4
4
 
5
5
  ## Install
6
6
 
@@ -100,18 +100,18 @@ askii do --dir .\my-project "refactor index.ts"
100
100
 
101
101
  The agent can use the following actions each round:
102
102
 
103
- | Action | Description | Requires confirmation |
104
- | ------------- | ----------------------------------------------------- | --------------------- |
105
- | `list` | List files in a folder (`[file]` / `[folder]` labels) | No |
106
- | `view` | Read a file's contents | No |
107
- | `search` | Grep workspace files for a pattern | No |
108
- | `wiki_search` | BM25 search over indexed `.md` docs (requires `--use-wiki`) | No |
109
- | `code_search` | BM25 search over indexed code files (requires `--use-code-wiki`) | No |
110
- | `create` | Create a new file | Yes |
111
- | `modify` | Replace text in an existing file | Yes |
112
- | `rename` | Rename or move a file | Yes |
113
- | `delete` | Delete a file | Yes |
114
- | `run` | Run a shell command | Yes (always) |
103
+ | Action | Description | Requires confirmation |
104
+ | ------------- | ---------------------------------------------------------------- | --------------------- |
105
+ | `list` | List files in a folder (`[file]` / `[folder]` labels) | No |
106
+ | `view` | Read a file's contents | No |
107
+ | `search` | Grep workspace files for a pattern | No |
108
+ | `wiki_search` | BM25 search over indexed `.md` docs (requires `--use-wiki`) | No |
109
+ | `code_search` | BM25 search over indexed code files (requires `--use-code-wiki`) | No |
110
+ | `create` | Create a new file | Yes |
111
+ | `modify` | Replace text in an existing file | Yes |
112
+ | `rename` | Rename or move a file | Yes |
113
+ | `delete` | Delete a file | Yes |
114
+ | `run` | Run a shell command | Yes (always) |
115
115
 
116
116
  The loop continues after every round — not only after reads — until the AI returns `[]` or the round limit is hit.
117
117
 
@@ -278,29 +278,32 @@ Without `--yes`, each proposed action is shown with its reasoning and requires `
278
278
 
279
279
  ## Options
280
280
 
281
- | Flag | Short | Description | Default |
282
- | ------------------- | ----- | --------------------------------------------------------- | ------------------------ |
283
- | `--platform` | `-p` | LLM platform: `ollama`, `lmstudio`, `openai`, `anthropic` | `ollama` |
284
- | `--ollama-url` | | Ollama server URL | `http://localhost:11434` |
285
- | `--lmstudio-url` | | LM Studio server URL | `ws://localhost:1234` |
286
- | `--ollama-model` | | Ollama model | `gemma3:270m` |
287
- | `--lmstudio-model` | | LM Studio model | `qwen/qwen3-coder-30b` |
288
- | `--openai-key` | | OpenAI API key (env: `ASKII_OPENAI_KEY`) | |
289
- | `--openai-model` | | OpenAI model | `gpt-4o` |
290
- | `--openai-url` | | OpenAI-compatible base URL (env: `ASKII_OPENAI_URL`) | |
291
- | `--anthropic-key` | | Anthropic API key (env: `ASKII_ANTHROPIC_KEY`) | |
292
- | `--anthropic-model` | | Anthropic model (env: `ASKII_ANTHROPIC_MODEL`) | `claude-opus-4-6` |
293
- | `--mode` | | Response style: `helpful`, `funny` | `funny` |
294
- | `--max-rounds` | | Max agent rounds for `do` / `control` / `browse` | `5` |
295
- | `--dir` | | Working directory for `do` | cwd |
296
- | `--code` | `-c` | Code input (alternative to stdin) | |
297
- | `--yes` | `-y` | Auto-confirm all actions | |
298
- | `--headless` | | Run Puppeteer headlessly for `browse` | `false` (visible) |
299
- | `--chrome-path` | | Path to Chrome/Chromium executable for `browse` | |
300
- | `--wiki-path` | | Path to folder with `.md` docs for wiki RAG (env: `ASKII_WIKI_PATH`) | |
301
- | `--use-wiki` | | Inject wiki context into `ask` / `edit` / `do` (env: `ASKII_USE_WIKI=1`) | |
302
- | `--code-wiki-path` | | Path to codebase root to index / search (env: `ASKII_CODE_WIKI_PATH`) | cwd |
303
- | `--use-code-wiki` | | Inject code wiki context into `ask` / `edit` / `do` (env: `ASKII_USE_CODE_WIKI=1`) | |
281
+ | Flag | Short | Description | Default |
282
+ | ------------------- | ----- | ---------------------------------------------------------------------------------- | ------------------------ |
283
+ | `--platform` | `-p` | LLM platform: `ollama`, `lmstudio`, `openai`, `anthropic`, `opencodego` | `ollama` |
284
+ | `--ollama-url` | | Ollama server URL | `http://localhost:11434` |
285
+ | `--lmstudio-url` | | LM Studio server URL | `ws://localhost:1234` |
286
+ | `--ollama-model` | | Ollama model | `gemma4:e4b` |
287
+ | `--lmstudio-model` | | LM Studio model | `qwen/qwen3-coder-30b` |
288
+ | `--openai-key` | | OpenAI API key (env: `ASKII_OPENAI_KEY`) | |
289
+ | `--openai-model` | | OpenAI model | `gpt-5-mini` |
290
+ | `--openai-url` | | OpenAI-compatible base URL (env: `ASKII_OPENAI_URL`) | |
291
+ | `--anthropic-key` | | Anthropic API key (env: `ASKII_ANTHROPIC_KEY`) | |
292
+ | `--anthropic-model` | | Anthropic model (env: `ASKII_ANTHROPIC_MODEL`) | `claude-sonnet-4-6` |
293
+ | `--opencodego-key` | | opencode Go API key (env: `ASKII_OPENCODEGO_KEY`) | |
294
+ | `--opencodego-model`| | opencode Go model (env: `ASKII_OPENCODEGO_MODEL`) | `glm-5.2` |
295
+ | `--opencodego-url` | | opencode Go base URL (env: `ASKII_OPENCODEGO_URL`) | `https://opencode.ai/zen/go/v1` |
296
+ | `--mode` | | Response style: `helpful`, `funny` | `funny` |
297
+ | `--max-rounds` | | Max agent rounds for `do` / `control` / `browse` | `5` |
298
+ | `--dir` | | Working directory for `do` | cwd |
299
+ | `--code` | `-c` | Code input (alternative to stdin) | |
300
+ | `--yes` | `-y` | Auto-confirm all actions | |
301
+ | `--headless` | | Run Puppeteer headlessly for `browse` | `false` (visible) |
302
+ | `--chrome-path` | | Path to Chrome/Chromium executable for `browse` | |
303
+ | `--wiki-path` | | Path to folder with `.md` docs for wiki RAG (env: `ASKII_WIKI_PATH`) | |
304
+ | `--use-wiki` | | Inject wiki context into `ask` / `edit` / `do` (env: `ASKII_USE_WIKI=1`) | |
305
+ | `--code-wiki-path` | | Path to codebase root to index / search (env: `ASKII_CODE_WIKI_PATH`) | cwd |
306
+ | `--use-code-wiki` | | Inject code wiki context into `ask` / `edit` / `do` (env: `ASKII_USE_CODE_WIKI=1`) | |
304
307
 
305
308
  ## Environment Variables
306
309
 
@@ -311,7 +314,7 @@ export ASKII_PLATFORM=ollama
311
314
 
312
315
  # Ollama
313
316
  export ASKII_OLLAMA_URL=http://localhost:11434
314
- export ASKII_OLLAMA_MODEL=gemma3:270m
317
+ export ASKII_OLLAMA_MODEL=gemma4:e4b
315
318
 
316
319
  # LM Studio
317
320
  export ASKII_LMSTUDIO_URL=ws://localhost:1234
@@ -319,12 +322,17 @@ export ASKII_LMSTUDIO_MODEL=qwen/qwen3-coder-30b
319
322
 
320
323
  # OpenAI
321
324
  export ASKII_OPENAI_KEY=sk-...
322
- export ASKII_OPENAI_MODEL=gpt-4o
325
+ export ASKII_OPENAI_MODEL=gpt-5-mini
323
326
  export ASKII_OPENAI_URL= # leave empty for api.openai.com
324
327
 
325
328
  # Anthropic
326
329
  export ASKII_ANTHROPIC_KEY=sk-ant-...
327
- export ASKII_ANTHROPIC_MODEL=claude-opus-4-6
330
+ export ASKII_ANTHROPIC_MODEL=claude-sonnet-4-6
331
+
332
+ # opencode Go
333
+ export ASKII_OPENCODEGO_KEY=...
334
+ export ASKII_OPENCODEGO_MODEL=glm-5.2
335
+ export ASKII_OPENCODEGO_URL=https://opencode.ai/zen/go/v1
328
336
 
329
337
  # Shared
330
338
  export ASKII_MODE=funny
@@ -347,7 +355,7 @@ $env:ASKII_PLATFORM = "ollama"
347
355
 
348
356
  # Ollama
349
357
  $env:ASKII_OLLAMA_URL = "http://localhost:11434"
350
- $env:ASKII_OLLAMA_MODEL = "gemma3:270m"
358
+ $env:ASKII_OLLAMA_MODEL = "gemma4:e4b"
351
359
 
352
360
  # LM Studio
353
361
  $env:ASKII_LMSTUDIO_URL = "ws://localhost:1234"
@@ -355,12 +363,17 @@ $env:ASKII_LMSTUDIO_MODEL = "qwen/qwen3-coder-30b"
355
363
 
356
364
  # OpenAI
357
365
  $env:ASKII_OPENAI_KEY = "sk-..."
358
- $env:ASKII_OPENAI_MODEL = "gpt-4o"
366
+ $env:ASKII_OPENAI_MODEL = "gpt-5-mini"
359
367
  $env:ASKII_OPENAI_URL = "" # leave empty for api.openai.com
360
368
 
361
369
  # Anthropic
362
370
  $env:ASKII_ANTHROPIC_KEY = "sk-ant-..."
363
- $env:ASKII_ANTHROPIC_MODEL = "claude-opus-4-6"
371
+ $env:ASKII_ANTHROPIC_MODEL = "claude-sonnet-4-6"
372
+
373
+ # opencode Go
374
+ $env:ASKII_OPENCODEGO_KEY = "..."
375
+ $env:ASKII_OPENCODEGO_MODEL = "glm-5.2"
376
+ $env:ASKII_OPENCODEGO_URL = "https://opencode.ai/zen/go/v1"
364
377
 
365
378
  # Shared
366
379
  $env:ASKII_MODE = "funny"
@@ -383,14 +396,14 @@ $env:ASKII_USE_CODE_WIKI = "1"
383
396
  **bash**
384
397
 
385
398
  ```bash
386
- ollama pull gemma3:270m
399
+ ollama pull gemma4:e4b
387
400
  askii ask "what is a closure?"
388
401
  ```
389
402
 
390
403
  **PowerShell**
391
404
 
392
405
  ```powershell
393
- ollama pull gemma3:270m
406
+ ollama pull gemma4:e4b
394
407
  askii ask "what is a closure?"
395
408
  ```
396
409
 
@@ -449,3 +462,23 @@ askii -p anthropic --anthropic-key sk-ant-... ask "what does this do?"
449
462
  askii -p anthropic --anthropic-key sk-ant-... --anthropic-model claude-sonnet-4-6 do "add error handling"
450
463
  askii -p anthropic --anthropic-key sk-ant-... --anthropic-model claude-haiku-4-5 explain "arr.reduce((a, b) => a + b, 0)"
451
464
  ```
465
+
466
+ ### opencode Go
467
+
468
+ A hosted, multi-model coding subscription ([opencode.ai/go](https://opencode.ai/go)). Most models use an OpenAI-compatible endpoint; Qwen and MiniMax models use an Anthropic-compatible one — ASKII routes automatically based on the model id. See the full model list at [opencode.ai/zen/go/v1/models](https://opencode.ai/zen/go/v1/models).
469
+
470
+ **bash**
471
+
472
+ ```bash
473
+ askii -p opencodego --opencodego-key ... ask "what does this do?"
474
+ askii -p opencodego --opencodego-key ... --opencodego-model kimi-k2.7-code do "add error handling"
475
+ askii -p opencodego --opencodego-key ... --opencodego-model qwen3.7-max explain "arr.reduce((a, b) => a + b, 0)"
476
+ ```
477
+
478
+ **PowerShell**
479
+
480
+ ```powershell
481
+ askii -p opencodego --opencodego-key ... ask "what does this do?"
482
+ askii -p opencodego --opencodego-key ... --opencodego-model kimi-k2.7-code do "add error handling"
483
+ askii -p opencodego --opencodego-key ... --opencodego-model qwen3.7-max explain "arr.reduce((a, b) => a + b, 0)"
484
+ ```