- Add huggingface to KnownProvider type
- Add HF_TOKEN env var mapping
- Process huggingface models from models.dev (14 models)
- Use openai-completions API with compat settings
- Add tests for all provider test suites
- Update documentation
fixes#994
Adds support for extended cache retention via PI_CACHE_RETENTION=long:
- Anthropic: 5m -> 1h TTL
- OpenAI: in-memory -> 24h retention
Only applies to direct API calls (api.anthropic.com, api.openai.com).
Proxies and other providers are unaffected.
fixes#967
- Merged theme.md content into themes.md
- Added hot reload documentation
- Updated all references from theme.md to themes.md
- Fixed outdated info (vars not defs, complete example with all 50 tokens)
- Removed dev-focused Implementation section
- Rewrote README intro to emphasize extensibility and pi packages
- Added Pi Packages section to README
- Created docs/packages.md covering install, sources, manifest, filtering
- Created docs/prompt-templates.md covering format and arguments
- Created docs/themes.md with overview linking to theme.md
I lost my ability to select up and down in the session selector because
of some hardcoded keybindings again... So, I am adding these
configurable keybindings so I can `ctrl+p` to select up :-)
### Changes
Adds 4 new keybinding actions for the session picker (/resume):
- `toggleSessionPath` (ctrl+p) - toggle path display
- `toggleSessionSort` (ctrl+r) - toggle sort mode
- `deleteSession` (ctrl+d) - delete selected session
- `deleteSessionNoninvasive` (ctrl+backspace) - delete when query empty
Refactors session-selector to use `kb.matches()` instead of hardcoded key checks.
* Add session renaming in interactive mode resume picker
Session list now displays last message timestamp as modified time
instead of file mtime. Ctrl+N enters rename mode in the interactive
resume picker, allowing quick session renaming without leaving the
selector. Rename hint is shown only in interactive mode, not in the
CLI --resume picker./
* Add docs entry for renaming in picker
* Update shortcut to ctrl+r for session renaming
- Add Ctrl+L (Open model selector) to /hotkeys command
- Add Alt+Enter (Queue follow-up message) to keyboard shortcuts table
- Add PageUp/PageDown (Scroll by page) to all documentation sections
- Add PackageSource type for npm/git sources with optional filtering
- Migrate npm:/git: sources from extensions to packages array
- Add getPackages(), setPackages(), setProjectPackages() methods
- Update package-manager to resolve from packages array
- Support selective loading: extensions, skills, prompts, themes per package
- Update pi list to show packages
- Add migration tests for settings
closes#645
Header values in models.json now resolve using the same logic as apiKey:
- Environment variable names are resolved to their values
- Shell commands prefixed with ! are executed
- Literal values are used directly
This is a minor breaking change: if a header value accidentally matches
an env var name, it will now resolve to that env var's value.
Fixes#909
- Add ResourceLoader interface and DefaultResourceLoader implementation
- Add PackageManager for npm/git extension sources with install/remove/update
- Add session.reload() and session.bindExtensions() APIs
- Add /reload command in interactive mode
- Add CLI flags: --skill, --theme, --prompt-template, --no-themes, --no-prompt-templates
- Add pi install/remove/update commands for extension management
- Refactor settings.json to use arrays for skills, prompts, themes
- Remove legacy SkillsSettings source flags and filters
- Update SDK examples and documentation for ResourceLoader pattern
- Add theme registration and loadThemeFromPath for dynamic themes
- Add getShellEnv to include bin dir in PATH for bash commands
Add markdown.codeBlockIndent setting to customize indentation prefix for
rendered code blocks. Default remains 2 spaces for visual clarity, but
setting to empty string removes indentation for easier copy/paste of
code snippets to scripts, editors, or other tools.
Changes:
- tui: add optional codeBlockIndent to MarkdownTheme interface
- coding-agent: add MarkdownSettings with codeBlockIndent property
- coding-agent: compose theme with settings at call sites (no global state)
- coding-agent: update message components to accept optional MarkdownTheme
Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
Fixes OpenAI Responses 400 error 'reasoning without following item' by
skipping errored/aborted assistant messages entirely rather than filtering
at the provider level. This covers openai-responses, openai-codex-responses,
and future providers.
Removes strictResponsesPairing compat option (no longer needed).
Closes#838
Undo snapshots are captured for all edit operations:
- Word insertion, backspace, forward delete
- Word/line deletion (Ctrl+W, Ctrl+U, Ctrl+K, Alt+D)
- Yank/yank-pop, paste, autocomplete completion
- Cursor movement starts a new undo unit
- setText() pushes snapshot when content changes
Additionally, history browsing captures the undo state on first entry.
Split OpenAICompat into OpenAICompletionsCompat and OpenAIResponsesCompat
for type-safe API-specific compat settings. Added strictResponsesPairing
option to suppress orphaned reasoning/tool calls on incomplete turns,
fixing 400 errors on Azure's Responses API which requires strict pairing.
Closes#768
* Support shell command execution for API key resolution in models.json
Add ! prefix support to apiKey field in models.json to execute shell commands
and use stdout as the API key. This allows users to store API keys in secure
credential managers like macOS Keychain, 1Password, Bitwarden, or HashiCorp Vault.
Example: "apiKey": "!security find-generic-password -ws 'anthropic'"
The apiKey field now supports three formats:
- !command - executes shell command, uses trimmed stdout
- ENV_VAR_NAME - uses environment variable value
- literal - uses value directly
fixes#697
* feat(coding-agent): cache API key command results for process lifetime
Shell commands (! prefix) are now executed once and cached. Environment
variables and literal values are not cached, so changes are picked up.
Addresses review feedback on #762.
---------
Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
When 429/500 errors occur during tool execution, empty assistant messages
with stopReason='error' get persisted. These break the tool_use -> tool_result
chain for Claude/Gemini APIs.
Added centralized filtering in transformMessages to skip assistant messages
with empty content and no tool calls. Provider-level filters remain for
defense-in-depth.
