feat(context)!: implement schema-based input for contexts

Redesign context provider input handling with JSON schema validation and
improved UX. Replace callback-based input with declarative schemas that
define available properties and constraints. This enables a more
consistent and maintainable approach for input handling across all
context providers.

Key improvements:
- Add schema property to context config for input validation
- Create functions to parse and describe schemas
- Implement unified input separator for multi-value parameters
- Update all built-in context providers to use schema-based input
- Improve prompt completion and documentation generation

BREAKING CHANGE: context.resolve now accepts table instead of string and context.input is built automatically, overriden through schema enum

Author: deathbeam

lua/CopilotChat/client.lua

@@ -1,7 +1,6 @@
 ---@class CopilotChat.Client.ask
 ---@field load_history boolean
 ---@field headless boolean
----@field contexts table<string, string>?
 ---@field selection CopilotChat.select.selection?
 ---@field embeddings table<CopilotChat.context.embed>?
 ---@field system_prompt string
@@ -201,49 +200,14 @@ end
 --- Generate ask request
 --- @param history table<CopilotChat.Provider.input>
 --- @param memory CopilotChat.Client.memory?
---- @param contexts table<string, string>?
 --- @param prompt string
 --- @param system_prompt string
 --- @param generated_messages table<CopilotChat.Provider.input>
-local function generate_ask_request(history, memory, contexts, prompt, system_prompt, generated_messages)
+local function generate_ask_request(history, memory, prompt, system_prompt, generated_messages)
   local messages = {}
 
   system_prompt = vim.trim(system_prompt)
 
-  -- Include context help
-  if contexts and not vim.tbl_isempty(contexts) then
-    local help_text = [[When you need additional context, request it using this format:
-
-> #<command>:`<input>`
-
-Examples:
-> #file:`path/to/file.js`        (loads specific file)
-> #buffers:`visible`             (loads all visible buffers)
-> #git:`staged`                  (loads git staged changes)
-> #system:`uname -a`             (loads system information)
-
-Guidelines:
-- Always request context when needed rather than guessing about files or code
-- Use the > format on a new line when requesting context
-- Output context commands directly - never ask if the user wants to provide information
-- Assume the user will provide requested context in their next response
-
-Available context providers and their usage:]]
-
-    local context_names = vim.tbl_keys(contexts)
-    table.sort(context_names)
-    for _, name in ipairs(context_names) do
-      local description = contexts[name]
-      description = description:gsub('\n', '\n   ')
-      help_text = help_text .. '\n\n - #' .. name .. ': ' .. description
-    end
-
-    if system_prompt ~= '' then
-      system_prompt = system_prompt .. '\n\n'
-    end
-    system_prompt = system_prompt .. help_text
-  end
-
   -- Include memory
   if memory and memory.content and memory.content ~= '' then
     if system_prompt ~= '' then
@@ -694,7 +658,7 @@ function Client:ask(prompt, opts)
 
   local headers = self:authenticate(provider_name)
   local request = provider.prepare_input(
-    generate_ask_request(history, self.memory, opts.contexts, prompt, opts.system_prompt, generated_messages),
+    generate_ask_request(history, self.memory, prompt, opts.system_prompt, generated_messages),
     options
   )
   local is_stream = request.stream