@denizokcu/haze 0.0.2 → 0.0.3

package/CHANGELOG.md

@@ -2,6 +2,16 @@
 
 ## Unreleased
 
+## 0.0.3 - 2026-06-06
+
+- Added stable transcript rendering for long sessions, compact placeholders for large multiline pastes, and clearer goal/status display.
+- Added OpenAI-compatible provider management with `/provider`, provider-qualified model selection, and legacy OpenRouter settings migration.
+- Added durable workspace sessions with `haze --continue`, `--no-session`, `/session`, `/resume`, `/new`, and `/compact`.
+- Added context compaction and goal-aware completion tracking to improve long-running agent turns.
+- Hardened file tools with structured recoverable failures, safer concurrent mutation handling, line-number-prefix tolerant edits, and EOF-clamped line replacements.
+- Simplified generated skill structure around role, focused prompt, and compact output templates.
+- Updated docs site install/version copy and refreshed dependencies.
+
 ## 0.0.2 - 2026-06-01
 
 - Reworked skills into Markdown-first workflows stored in `~/.haze/skills/<name>/SKILL.md`.

package/README.md

@@ -2,9 +2,13 @@
 
 A minimal LLM harness for your terminal.
 
+## What's new in 0.0.3
+
+Haze 0.0.3 keeps long sessions calmer with stable transcript rendering, compact placeholders for large multiline pastes, and clearer goal/status display. Pasted text is still sent to the model with line breaks preserved.
+
 Haze gives an AI model a small set of transparent local tools — read files, edit files, write files, list files, and run commands — then gets out of the way. Start with chat. Build your workflows as you work. Teach Haze with Markdown skills when a pattern repeats. Tiny spell, useful goblin.
 
-MVP scope: Haze currently uses OpenRouter only. More providers are on the roadmap after the goblin learns to hold a spoon safely.
+Haze works with OpenAI-compatible providers, including OpenRouter and local endpoints. Use `/provider` to choose or add one, then `/model` to select a model.
 
 ```txt
   _
@@ -17,30 +21,48 @@ MVP scope: Haze currently uses OpenRouter only. More providers are on the roadma
 
 Haze keeps guardrails light. The LLM can work from the terminal with freedoms close to yours, while trying to stay scoped to the current project. Watch the tool calls. Keep your hands near the wheel. Progress.
 
-## Install
+## Getting started
+
+Install Haze:
 
 ```bash
 npm install -g @denizokcu/haze
-haze
 ```
 
-First run inside Haze, do both steps:
+Open Haze from your project:
+
+```bash
+$ haze
+```
+
+On first run, create or choose a provider, then choose your first model:
 
 ```txt
-/login
-/model x-ai/grok-build-0.1
+/provider
+/model
 ```
 
-`/login` saves your API key. `/model` saves the model Haze should use. The recommended MVP model is `x-ai/grok-build-0.1`.
+`/provider` opens provider setup for any OpenAI-compatible endpoint — e.g. OpenRouter, OpenAI, LM Studio, Ollama, or a proxy. Haze will ask for a provider name, base URL, optional API key, and model names.
+
+`/model` selects the model Haze should use. You can also set one directly:
+
+```txt
+/model x-ai/grok-build-0.1
+/model local:llama3.1
+```
 
-Or use environment variables:
+Or use environment variables for any OpenAI-compatible endpoint:
 
 ```bash
-export OPENAI_API_KEY=... # your OpenRouter API key
-export HAZE_MODEL=x-ai/grok-build-0.1
+# e.g. OpenRouter, OpenAI, LM Studio, Ollama, or an OpenAI-compatible proxy
+export OPENAI_API_KEY=... # provider API key, if needed; local providers may not need one
+export OPENAI_BASE_URL=https://openrouter.ai/api/v1 # or http://localhost:1234/v1, http://localhost:11434/v1, ...
+export HAZE_MODEL=x-ai/grok-build-0.1 # or gpt-4.1, llama3.1, qwen2.5-coder, ...
 ```
 
-Saved settings live in `~/.haze/settings.json`. The current MVP experience is documented around OpenRouter; more provider docs are future work.
+Saved settings live in `~/.haze/settings.json`. Providers can include API keys, base URLs, and model lists; local OpenAI-compatible providers can be configured without a key.
+
+Haze is intentionally minimal: chat, local tools, context files, sessions, and Markdown skills. Any workflow beyond the core is meant to be grown with the LLM through `/create-skill <description>`. If you want reviews, release prep, deploy checks, debugging rituals, or your team's strange checklist, ask Haze to create a skill and then refine the Markdown.
 
 ## Get productive immediately
 
@@ -50,7 +72,7 @@ Open a project and ask for work:
 create a calculator in calc-app in ruby with add subtract multiply divide
 ```
 
-Haze will inspect, write files, run commands, and show compact tool activity inline.
+Haze will inspect, write files, run commands, and show compact tool activity inline. Sessions are saved by default so you can resume the latest workspace conversation with `haze --continue` or `/resume`.
 
 Use `/` to discover commands and skills. `Tab` completes the top suggestion.
 
@@ -58,30 +80,30 @@ Useful starters:
 
 ```txt
 /init
-/skill create review my current branch against main like a senior engineer
-/skill create prepare clean git commits from my uncommitted changes
-/skill create implement small features with tests and a concise summary
+/create-skill review my current branch against main like a senior engineer
+/create-skill prepare clean git commits from my uncommitted changes
+/create-skill implement small features with tests and a concise summary
 ```
 
 `/init` creates or updates `AGENTS.md` so future sessions understand the project.
 
 ## Skills: your workflows, grown while working
 
-Skills are Markdown workflows stored in `~/.haze/skills`.
+Skills are Markdown workflows that Haze creates with `/create-skill` and stores in `~/.haze/skills` so you can inspect or refine them later.
 
-When you notice yourself asking for the same kind of work, make it a skill:
+If you do something for the second time, build a skill for it:
 
 ```txt
-/skill create review the diff between my current branch and main, focusing on bugs, tests, DRY and KISS
+/create-skill review the diff between my current branch and main, focusing on bugs, tests, DRY and KISS
 ```
 
-Haze uses the model to create:
+Haze uses the model to create the skill file for you:
 
 ```txt
 ~/.haze/skills/<skill-name>/SKILL.md
 ```
 
-A skill is just Markdown with frontmatter:
+A skill is just Markdown with frontmatter, a role, a focused prompt, and a small output template:
 
 ```md
 ---
@@ -89,13 +111,28 @@ name: code-review-diff-main
 description: Use when the user asks for a code review of the current branch against main.
 ---
 
-# Goal
+# Role
+
+You are a focused code reviewer.
+
+# Focused prompt
 
 Review the actual change and return useful, evidence-based feedback.
 
 # Procedure
 
 Inspect branch state, changed files, staged and unstaged diffs, then review incrementally.
+
+# Output template
+
+## Summary
+- <scope and result>
+
+## Findings
+- <prioritized findings, or "No issues found">
+
+## Evidence inspected
+- <commands/files used>
 ```
 
 Installed skills appear as slash commands like:
@@ -112,22 +149,35 @@ This is the trick: do normal work, notice friction, create a skill, keep going.
 
 ```txt
 /help
-/login
-/model <name>
+/provider
 /model
+/model <name-or-provider:name>
+/model list
 /settings
 /init
+/session
+/resume
+/new
+/compact [instructions]
 /clear
 /exit
 
-/skill create <description>
-/skill list
-/skill info <name>
-/skill validate <name-or-dir>
-/skill remove <name> --yes
+/create-skill <description>
+/list-skills
+/skill-info <name>
+/validate-skill <name-or-dir>
+/remove-skill <name> --yes
 ```
 
-`/skills ...` also works as an alias for `/skill ...`.
+Legacy `/skill ...` and `/skills ...` commands still work as aliases.
+
+CLI flags:
+
+```bash
+haze --debug       # show model/tool debug logs
+haze --continue    # resume the latest saved session for this workspace
+haze --no-session  # run without durable session storage
+```
 
 ## Agent tools
 
@@ -135,16 +185,18 @@ Haze exposes a deliberately small toolset:
 
 - `listFiles` — structured discovery, recursive with cursor pagination when needed.
 - `readFile` — read UTF-8 files with optional line ranges.
-- `editFile` — exact unique text replacements.
-- `replaceLines` — line-range edits when exact replacements are awkward.
+- `editFile` — unique text replacements, with line-number-prefix tolerance for common model mistakes.
+- `replaceLines` — line-range edits when exact replacements are awkward; slightly-too-large EOF ranges are clamped.
 - `writeFile` — create files and parent directories.
 - `bash` — run tests, builds, git commands, and inspections.
 - `skill_*` — load Markdown skill instructions on demand.
 
-Tool calls are grouped in the transcript so you can see what happened without reading a novella.
+Tool calls are grouped in the transcript so you can see what happened without reading a novella. File-tool failures return structured recovery hints instead of mystery stack traces.
 
 ## Context files
 
+Haze saves durable workspace sessions in `~/.haze/sessions`. Use `/session` to see the current file, `/new` to start fresh, `/resume` to restore the latest session, and `/compact` to summarize older model context while keeping recent messages.
+
 Haze loads project instructions from:
 
 - `~/.haze/AGENTS.md`
@@ -180,12 +232,14 @@ Package check:
 npm pack --dry-run
 ```
 
-The npm package ships `bin`, `dist`, docs, license, changelog, and examples.
+The npm package ships `bin`, `dist`, README, license, changelog, and examples.
 
 ## Release
 
 ```bash
 npm run typecheck
+npm test
+npm run lint
 npm run build
 npm pack --dry-run
 git tag vX.Y.Z

package/dist/cli/commands/chat.d.ts

@@ -1,7 +1,9 @@
-export type Mode = 'chat' | 'apiKey' | 'model';
+export type Mode = 'chat' | 'provider' | 'providerAction' | 'model' | 'providerAddName' | 'providerAddUrl' | 'providerAddKey' | 'providerAddModels' | 'providerAppendModels';
 interface ChatOptions {
     debug?: boolean;
     version?: string;
+    continueSession?: boolean;
+    noSession?: boolean;
 }
 export declare function chatCommand(options?: ChatOptions): Promise<void>;
 export {};