llm.rb 12.3.1 → 12.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a1be1cd2af0cc8a817e510b04d1d74efd08cedf714b3faff4bdb7a58345fe14f
-  data.tar.gz: 3768fdf7f131d30c04d0ba83514bec31eb8d64de661980aa811a4e804a4df1e5
+  metadata.gz: cd29af290d188d501b82ef31aae35258d7b6987b14f51bdce68dfbcc3bdca671
+  data.tar.gz: 4def59348a5f33bd66248e654f75de05adc7bd8d188686c9464bcfca12a61dcb
 SHA512:
-  metadata.gz: 667c546559bb199c7381fbea97171b5e82e874098c40a763004db85667038aa430fa98592c4d42b1426e4536e288e70c018278b9e7af9fcf9b6d972eabd65cbe
-  data.tar.gz: 0163f85848ce7292905396458755d9ccb23298c6f7c6f06cf0532fb3bdb3517e1b188a022937eb540b823d82d7bc8d869549bc17c8d79767c5efe027bf5ae9be
+  metadata.gz: da29e5f492f1130249d5db09ce098aff34d6805d16ed1d8e6df120a3038c4e013dc4dc95a16fcf39dd68f5eacc813715a41c1de7b61befa28206914a26c1aa32
+  data.tar.gz: 310c5dab18e187fd8aabd66c363e192a0b556b7f26efd2d7c553416b60782921da94feec04b834549b023ac5f3064c74e411aa32e5981782b237aabe9938d1fb

data/CHANGELOG.md

@@ -15,8 +15,163 @@
 
 ## What's next
 
+Changes since `v12.4.0`.
+
+## v12.4.0
+
 Changes since `v12.3.1`.
 
+This release brings major improvements to the curses-based REPL
+(`LLM::Agent#repl`). The REPL now supports saving and restoring runtime
+state across sessions, automatic paste-mode detection for fast bulk input,
+a command system foundation with the `/exit` command, and several new
+keybindings (Ctrl+F, Ctrl+K, Ctrl+Y). Tool calls are rendered with a
+compact function-call syntax in the status bar.
+
+Two new built-in tools — `LLM::Tool::Ls` and `LLM::Tool::Which` — are
+available as opt-in additions for file listing and executable lookup.
+
+Model metadata has been refreshed across providers, the REPL loop
+internals have been refactored to use `catch`/`throw` for cleaner command
+routing, and several bugs have been fixed including a tracer restoration
+issue in the agent ensure clause and a missing cursor in the REPL input
+area.
+
+### Add
+
+* **repl: allow runtime state to be saved and restored** <br>
+  `LLM::Agent#repl` now accepts a `path:` option that serializes
+  runtime state to the filesystem. When the path already exists,
+  runtime state is restored when the read-eval-print loop starts.
+  Otherwise the path is written after the first turn, making it
+  possible to resume a session across process restarts.
+
+* **repl: scroll to the bottom on submit** <br>
+  The curses-based REPL now scrolls the transcript to the bottom when
+  the user submits their input, so the latest response is visible
+  without needing to scroll down manually.
+
+* **repl: add Ctrl+F to move the cursor forward** <br>
+  The curses-based REPL input now supports Ctrl+F to move the cursor
+  forward by one column, matching common terminal editing conventions
+  found in shells like `/bin/sh`.
+
+* **repl: add Ctrl+K to erase from cursor to end of line** <br>
+  The curses-based REPL input now supports Ctrl+K to erase all text
+  from the cursor position to the end of the input buffer, matching
+  common terminal editing conventions found in shells like `/bin/sh`.
+
+* **repl: add Ctrl+Y to paste previously killed text** <br>
+  The curses-based REPL input now supports Ctrl+Y to insert the most
+  recently killed text (via Ctrl+K) at the current cursor position,
+  matching the yank/paste convention found in shells like `/bin/sh`.
+  The killed text is stored in an internal copy buffer so it can be
+  pasted multiple times or at different cursor positions.
+
+* **repl: add command system foundation** <br>
+  Add `LLM::Repl::Command` as a new base class for REPL commands,
+  along with the first built-in command `LLM::Repl::Command::Exit`
+  which exits the read-eval-print loop via `throw(:exit)`.
+  Commands are identified by a name and can be looked up through
+  `Command.find_by`. This is the foundation for the `/` command
+  syntax used in the REPL input line.
+
+* **repl: connect the command system to user input** <br>
+  The curses-based REPL now routes user input through the command
+  system. Any input string beginning with `"/"` is matched against
+  the command registry via `Command.find_by`, and the corresponding
+  command is executed instead of being forwarded to the model.
+  This makes built-in commands like `/exit` functional from the
+  input line. Command arguments are not yet supported.
+
+* **repl: add `LLM::Repl::Command.registry`** <br>
+  Add `LLM::Repl::Command.registry` for auto-registering command
+  subclasses. The `inherited` hook captures each new subclass and
+  stores it in the registry, making it possible to enumerate all
+  available commands at runtime. Built-in commands like Exit are
+  automatically registered when the command file is loaded.
+
+* **repl: detect and handle paste mode in the input line** <br>
+  The curses-based REPL input now detects paste operations by tracking
+  the rate at which characters arrive. A paste rate of ≤50ms is
+  assumed to be a burst of characters that could only be explained by
+  a paste — no human types that fast. Multiline pastes are supported
+  through internal refactoring of the input handling logic.
+
+* **repl: optimize paste mode rendering** <br>
+  Track the paste state with an internal `@paste` variable and switch
+  to a faster input path during paste operations. While in paste mode,
+  the input buffer is drained via `Curses.getch`, bypassing the more
+  expensive char-by-char render path used for ordinary interactive
+  input. This makes pasting large amounts of text noticeably faster.
+
+* **Add `LLM::Tool::Ls`** <br>
+  Add a built-in tool for listing files and directories, with optional
+  glob pattern filtering to narrow results. <br>
+  It must be required explicitly with `require "llm/tools/ls"`.
+
+* **Add `LLM::Tool::Which`** <br>
+  Add a built-in tool for locating an executable on the system PATH.
+  This lets an agent check whether a command is available before
+  attempting to run it, avoiding failed subprocess calls. <br>
+  It must be required explicitly with `require "llm/tools/which"`.
+
+* **repl: render tool calls in a function-call syntax** <br>
+  The curses-based REPL status bar now renders tool calls with a
+  compact function-call syntax — `tool(key: value)` instead of
+  `tool: name`. Strings are quoted and truncated, arrays show their
+  first two elements, and hashes collapse to `{…}`, making it easier
+  to see what arguments the model is passing. The `tool done` status
+  message has been removed since the tool call itself conveys
+  completion information.
+
+### Change
+
+* **Refresh model metadata** <br>
+  Update model listings, pricing, and capabilities across providers.
+  Fix GPT-5.6 model family names in the OpenAI registry (`gpt` to
+  `gpt-sol`, `gpt-nano` to `gpt-luna`, `gpt-mini` to `gpt-terra`).
+  Add OpenAI models (`gpt-5.6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`)
+  to the AWS Bedrock registry. Update DeepInfra pricing for
+  `DeepSeek-V3` and `Sky-T1-32B-Preview`. Fix Google model knowledge
+  cutoff dates.
+
+* **repl: control the loop with catch & throw** <br>
+  The curses-based REPL input loop now uses `catch(:exit)` and
+  `throw(:exit)` instead of returning the `:exit` symbol and
+  breaking out of the loop. This enables the `/command` syntax
+  without requiring an `:exit` return value to be propagated
+  through a potentially deeply nested call path.
+
+* **repl: replace Ctrl+D with shell-like delete-at-cursor** <br>
+  The curses-based REPL input now treats Ctrl+D as a delete action
+  that removes the character at the current cursor position, matching
+  the shell/Emacs convention where Ctrl+D deletes the character under
+  the cursor instead of signalling end-of-file. The previous Ctrl+D
+  behaviour (exiting the REPL) is superseded by the `/exit` command.
+
+* **repl: switch to 'Thinking' mode after tool return** <br>
+  The curses-based REPL status line now switches to "Thinking" mode
+  after a tool returns, so the user can see the agent is processing
+  the tool result rather than showing a stale tool-call status.
+
+### Fix
+
+* **agent: fix a subtle typo in the ensure clause** <br>
+  Fix a subtle typo in `LLM::Agent` where the deprecated `trace` local
+  variable was given preference over `tracer` (the preferred local name)
+  in an `ensure` clause. The `trace` local was supported for backward
+  compatibility but the ensure clause still referenced `trace` instead of
+  `tracer`, which meant the previous tracer was never restored when the
+  REPL session ended.
+
+* **repl: restore the cursor in the input area** <br>
+  Remove the `Curses.curs_set(0)` call from the REPL redraw method,
+  which was inadvertently hiding the cursor and making it impossible
+  to see the current position in the input area. The input field is
+  now always drawn at its full height so the cursor position is
+  correctly maintained after each redraw.
+
 ## v12.3.1
 
 Changes since `v12.3.0`.

data/README.md

@@ -129,28 +129,50 @@ This feature requires that the [curses](https://github.com/ruby/curses)
 and [kramdown](https://github.com/gettalong/kramdown) libraries are
 installed and available to require.
 
+The TUI displays a status line with a context-usage bar and cost
+counter, a scrollable transcript with markdown rendering, and a
+multi-line input area. The UI stays responsive while the model
+is generating a response.
+
+##### REPL: Agent
+
+A REPL session is started by calling `repl` on any agent
+instance. The session inherits the agent's model, tools,
+skills, and instructions.
+
 ```ruby
 llm = LLM.deepseek(key: ENV["KEY"])
 agent = LLM::Agent.new(llm)
 agent.repl
 ```
 
-The read-eval-print loop accepts both `tools` and `skills`
-options that lets you attach additional tools or skills
-for the duration of the session. This is in addition to
-any tools or skills that might already be associated with
-an agent.
+##### REPL: State
+
+The `path:` option accepts a file path where runtime state
+is read from and written to. This lets you resume a
+conversation across REPL sessions.
 
 ```ruby
 llm = LLM.deepseek(key: ENV["KEY"])
 agent = LLM::Agent.new(llm)
-agent.repl(tools: [Debugger], skills: [__dir__])
+agent.repl(path: "session.json")
 ```
 
-A number of optional tools are distributed as part
-of llm.rb. They power the agents that can be found in
-the [agents/](agents/) directory, so they're optimized
-for developer tasks.
+##### REPL: Tools
+
+The `tools` option lets you attach additional tools
+for the duration of the session. This is in addition to
+any tools that might already be associated with an agent.
+
+A number of optional tools are distributed as part of
+llm.rb. They power the agents that can be found in the
+[agents/](agents/) directory.
+
+```ruby
+llm = LLM.deepseek(key: ENV["KEY"])
+agent = LLM::Agent.new(llm)
+agent.repl(tools: [Debugger])
+```
 
 The following example starts a read-eval-print loop
 with all of the builtin tools available.
@@ -164,11 +186,23 @@ agent = LLM::Agent.new(llm)
 agent.repl(tools: LLM::Tool.subclasses)
 ```
 
-By default the tracer is disabled for the duration of
-the session. This can be configured through the
-`tracer` option. Setting it to `true` will configure
-the REPL to use the tracer associated with an instance
-of [`LLM::Agent`](https://r.uby.dev/api-docs/llm.rb/LLM/Agent.html).
+##### REPL: Skills
+
+The `skills` option lets you load extra skill directories
+without attaching them to an agent permanently.
+
+```ruby
+llm = LLM.deepseek(key: ENV["KEY"])
+agent = LLM::Agent.new(llm)
+agent.repl(skills: [__dir__])
+```
+
+##### REPL: Tracer
+
+By default the tracer is disabled for the duration of the
+session. Setting `tracer: true` configures the REPL to use
+the tracer associated with an instance of
+[`LLM::Agent`](https://r.uby.dev/api-docs/llm.rb/LLM/Agent.html).
 
 ```ruby
 llm = LLM.deepseek(key: ENV["KEY"])
@@ -176,6 +210,29 @@ agent = LLM::Agent.new(llm, tracer: LLM.logger(llm, path: "agent.log"))
 agent.repl(tracer: true, tools: [Debugger])
 ```
 
+##### REPL: Input
+
+The input area supports several keyboard shortcuts:
+
+| Key | Action |
+|---|---|
+| `Enter` | Submit the current prompt |
+| `Ctrl+A` | Jump to the start of the line |
+| `Ctrl+E` | Jump to the end of the line |
+| `Ctrl+F` | Move the cursor forward |
+| `Ctrl+K` | Erase from cursor to the end of the line |
+| `Ctrl+Y` | Paste previously killed text |
+| `Ctrl+D` | Delete the character at the cursor |
+| `Left / Right` | Move the cursor |
+| `Up / Down` | Scroll the transcript |
+| `/exit` | Leave the REPL |
+
+##### REPL: Commands
+
+Commands are recognized by a `/` prefix and are backed by the
+[`LLM::Repl::Command`](https://r.uby.dev/api-docs/llm.rb/LLM/Repl/Command.html)
+class, which can be subclassed to add custom commands.
+
 #### LLM::MCP
 
 The Model Context Protocol (MCP) has first-class support

data/data/bedrock.json

@@ -1064,6 +1064,59 @@
         "output": 2.75
       }
     },
+    "openai.gpt-5.6-luna": {
+      "id": "openai.gpt-5.6-luna",
+      "name": "GPT-5.6 Luna",
+      "description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
+      "family": "gpt-luna",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "knowledge": "2026-02-16",
+      "release_date": "2026-07-09",
+      "last_updated": "2026-07-09",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 272000,
+        "output": 128000
+      },
+      "provider": {
+        "npm": "@ai-sdk/amazon-bedrock/mantle",
+        "api": "https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1",
+        "shape": "responses"
+      },
+      "cost": {
+        "input": 1,
+        "output": 6,
+        "cache_read": 0.1,
+        "cache_write": 1.25
+      }
+    },
     "openai.gpt-oss-safeguard-120b": {
       "id": "openai.gpt-oss-safeguard-120b",
       "name": "GPT OSS Safeguard 120B",
@@ -2520,6 +2573,59 @@
         "cache_read": 0.015
       }
     },
+    "openai.gpt-5.6-sol": {
+      "id": "openai.gpt-5.6-sol",
+      "name": "GPT-5.6 Sol",
+      "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
+      "family": "gpt-sol",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "knowledge": "2026-02-16",
+      "release_date": "2026-07-09",
+      "last_updated": "2026-07-09",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 272000,
+        "output": 128000
+      },
+      "provider": {
+        "npm": "@ai-sdk/amazon-bedrock/mantle",
+        "api": "https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1",
+        "shape": "responses"
+      },
+      "cost": {
+        "input": 5,
+        "output": 30,
+        "cache_read": 0.5,
+        "cache_write": 6.25
+      }
+    },
     "us.anthropic.claude-haiku-4-5-20251001-v1:0": {
       "id": "us.anthropic.claude-haiku-4-5-20251001-v1:0",
       "name": "Claude Haiku 4.5 (US)",
@@ -4037,6 +4143,59 @@
         "cache_write": 3.75
       }
     },
+    "openai.gpt-5.6-terra": {
+      "id": "openai.gpt-5.6-terra",
+      "name": "GPT-5.6 Terra",
+      "description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
+      "family": "gpt-terra",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "knowledge": "2026-02-16",
+      "release_date": "2026-07-09",
+      "last_updated": "2026-07-09",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 272000,
+        "output": 128000
+      },
+      "provider": {
+        "npm": "@ai-sdk/amazon-bedrock/mantle",
+        "api": "https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1",
+        "shape": "responses"
+      },
+      "cost": {
+        "input": 2.5,
+        "output": 15,
+        "cache_read": 0.25,
+        "cache_write": 3.125
+      }
+    },
     "google.gemma-3-12b-it": {
       "id": "google.gemma-3-12b-it",
       "name": "Google Gemma 3 12B",

data/data/deepinfra.json

@@ -33,8 +33,8 @@
         "output": 16384
       },
       "cost": {
-        "input": 0.15,
-        "output": 0.6
+        "input": 0.2,
+        "output": 0.8
       }
     },
     "meta-llama/Llama-4-Scout-17B-16E-Instruct": {
@@ -1065,9 +1065,9 @@
         "output": 131072
       },
       "cost": {
-        "input": 0.43,
-        "output": 1.74,
-        "cache_read": 0.08
+        "input": 0.5,
+        "output": 2,
+        "cache_read": 0.1
       }
     },
     "zai-org/GLM-5": {

data/data/google.json

@@ -491,7 +491,7 @@
       "reasoning_options": [],
       "tool_call": false,
       "temperature": true,
-      "knowledge": "2025-06",
+      "knowledge": "2024-06",
       "release_date": "2025-08-26",
       "last_updated": "2025-08-26",
       "modalities": {

data/data/openai.json

@@ -128,7 +128,7 @@
       "id": "gpt-5.6",
       "name": "GPT-5.6",
       "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
-      "family": "gpt",
+      "family": "gpt-sol",
       "attachment": true,
       "reasoning": true,
       "reasoning_options": [
@@ -1027,7 +1027,7 @@
       "id": "gpt-5.6-luna",
       "name": "GPT-5.6 Luna",
       "description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
-      "family": "gpt-nano",
+      "family": "gpt-luna",
       "attachment": true,
       "reasoning": true,
       "reasoning_options": [
@@ -1214,7 +1214,7 @@
       "id": "gpt-5.6-terra",
       "name": "GPT-5.6 Terra",
       "description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
-      "family": "gpt-mini",
+      "family": "gpt-terra",
       "attachment": true,
       "reasoning": true,
       "reasoning_options": [
@@ -2184,7 +2184,7 @@
       "id": "gpt-5.6-sol",
       "name": "GPT-5.6 Sol",
       "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
-      "family": "gpt",
+      "family": "gpt-sol",
       "attachment": true,
       "reasoning": true,
       "reasoning_options": [

data/lib/llm/agent.rb

@@ -398,15 +398,18 @@ module LLM
     #  By default this method disables the tracer for
     #  the duration of the repl session, and restores
     #  it afterwards.
-    # @param [Boolean] tracer
-    #  When true, the tracer is kept alive during the
-    #  repl session. Default is false.
+    # @param [String] path
+    #  The path to a file where runtime state is read
+    #  from, and written to
     # @param [Array<LLM::Tool>] tools
     #  Extra tools to attach for the repl session
     # @param [Array<String>] skills
     #  Extra skills to attach for the repl session
+    # @param [Boolean] tracer
+    #  When true, the tracer is kept alive during the
+    #  repl session. Default is false.
     # @return [void]
-    def repl(tracer: false, trace: nil, tools: [], skills: [])
+    def repl(path: nil, tools: [], skills: [], tracer: false, trace: nil)
       if trace != nil
         warn "llm.rb: trace option is deprecated, use tracer instead"
         tracer = trace
@@ -416,9 +419,9 @@ module LLM
         self.tracer = nil
       end
       require_relative "repl" unless defined?(::LLM::Repl)
-      LLM::Repl.new(agent: self, tools:, skills:).start
+      LLM::Repl.new(agent: self, path:, tools:, skills:).start
     ensure
-      if !trace
+      if !tracer
         self.tracer = previous
       end
     end

data/lib/llm/context/deserializer.rb

@@ -31,9 +31,8 @@ class LLM::Context
     end
     alias_method :restore, :deserialize
 
-    ##
-    # @param [Hash] payload
-    # @return [LLM::Message]
+    private
+
     def deserialize_message(payload)
       tool_calls = deserialize_tool_calls(payload["tools"])
       returns = deserialize_returns(payload["content"]) if returns.nil?
@@ -46,8 +45,6 @@ class LLM::Context
       LLM::Message.new(payload["role"], content, extra)
     end
 
-    private
-
     def deserialize_content(content)
       case content
       when Array