* feat(coding-agent,tui): support argument-hint frontmatter in prompt templates
Parse argument-hint from prompt template frontmatter and display it
in the autocomplete dropdown description, matching Claude Code's
convention for custom commands.
Frontmatter format:
---
description: Code review
argument-hint: "[file | #PR | PR-URL]"
---
The hint renders in the description column of the autocomplete list:
review [file | #PR | PR-URL] — Code review
Closes#2761
* docs(coding-agent,tui): add argument-hint documentation, tests, and built-in hints
- Document argument-hint frontmatter in prompt-templates.md with <required>/[optional] convention
- Add argument-hint to built-in prompts: pr, is, wr
- Expand tests: required/optional hints, missing hints, empty hints, special characters
- Add changelog entries for coding-agent and tui
This reverts 3929e0c181.
The Zellij-specific Kitty-query skip regresses Shift+Enter newline handling in Zellij. Restoring the previous behavior for now while we work on a safer fix that preserves both Alt and modified Enter handling.\n\nContext: https://github.com/badlogic/pi-mono/issues/3259
The OpenRouterRouting interface only had only and order, but the runtime
passes the entire object as-is to the OpenRouter API's provider field.
This means all other fields worked at runtime but had no TypeScript
type-checking, no autocomplete, and no config validation.
This adds all fields from the OpenRouter provider selection API
(https://openrouter.ai/docs/guides/routing/provider-selection):
allow_fallbacks, require_parameters, data_collection, zdr,
enforce_distillable_text, ignore, quantizations, sort, max_price,
preferred_min_throughput, preferred_max_latency.
Also fixes the models.md documentation which had an invalid fallbacks
field in the example (not part of the OpenRouter API), replaces it with
a comprehensive example showing all available fields, and clarifies that
openRouterRouting is sent as-is in the provider field.
Add AgentTool.prepareArguments and ToolDefinition.prepareArguments hook
that runs before schema validation in the agent loop. This lets tools
silently accept legacy argument shapes from resumed old sessions without
polluting the public schema.
The built-in edit tool uses this to fold legacy top-level oldText/newText
into edits[] when resuming sessions that predate the edits-only schema.
- AgentTool/ToolDefinition: typed prepareArguments returning Static<TParameters>
- agent-loop: prepareToolCallArguments() runs before validateToolArguments()
- edit tool: prepareEditArguments folds legacy fields, validateEditInput is strict
- Documented in extensions.md with edit-tool example
Users can now set sessionDir in global or project settings.json instead
of passing --session-dir on every invocation. CLI flag takes precedence,
then settings.json, then extension hooks.
Closes#2429
Co-authored-by: Sam Collins <81678+smcllns@users.noreply.github.com>
Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
Add AWS_BEDROCK_FORCE_CACHE=1 environment variable support. When the
model ID doesn't contain a recognizable Claude model name, users can
set this variable to force cache point injection.