wip

2026-04-28 02:11:08 +03:00 · 2025-06-24 20:27:57 -07:00
parent 771294f65d
commit d07d7a7440
13 changed files with 79 additions and 71 deletions
--- a/agentydragon/tasks/19-bash-command-rendering-improvements.md
+++ b/agentydragon/tasks/19-bash-command-rendering-improvements.md
@@ -1,16 +1,4 @@
---
-id: 19
-title: Bash Command Rendering Improvements for Less Verbosity
-status: Not started
-dependencies: "02,07,09,11,14,29"
-summary: Render bash commands more concisely and shorten tool output annotations.
-goal: |
-  Adjust agent output formatting for shell commands and tool logs to:
-  - Render bash commands without wrapping them in `bash -lc "..."`.
-  - Display role-prefixed messages on a single line (role and content space-separated).
-  - Shorten command-result annotations, using `✅ <duration>ms` for successful runs or `exit code: <code> <duration>ms` for failures.
-
-++
+++
 id = "19"
 title = "Bash Command Rendering Improvements for Less Verbosity"
 status = "Not started"
--- a/agentydragon/tasks/21-compact-markdown-rendering.md
+++ b/agentydragon/tasks/21-compact-markdown-rendering.md
@@ -1,10 +1,10 @@
---
+++
 id = "21"
 title = "Compact Markdown Rendering Option"
 status = "Not started"
 dependencies = "03,06,08,13,15,32,18,19,22,23"
 last_updated = "2025-06-25T01:40:09.600000"
-++
+++

 ## Summary
 Provide an option to render Markdown without blank lines between headings and content for more vertical packing.
--- a/agentydragon/tasks/22-message-rendering-layout-options.md
+++ b/agentydragon/tasks/22-message-rendering-layout-options.md
@@ -1,10 +1,10 @@
---
+++
 id = "22"
 title = "Message Separation and Sender-Content Layout Options"
 status = "Not started"
 dependencies = "02,07,09,11,14,29"
 last_updated = "2025-06-25T01:40:09.600000"
-++
+++

 ## Summary
 Add configurable options for inter-message spacing and sender-content line breaks in chat rendering.
--- a/agentydragon/tasks/23-interactive-container-command-affordance.md
+++ b/agentydragon/tasks/23-interactive-container-command-affordance.md
@@ -1,10 +1,10 @@
---
+++
 id = "23"
 title = "Interactive Container Command Affordance via Hotkey"
 status = "Not started"
 dependencies = "02,07,09,11,14,29"
 last_updated = "2025-06-25T01:40:09.600000"
-++
+++

 ## Summary
 Provide a keybinding to run arbitrary shell commands in the agent’s container and display output inline.
--- a/agentydragon/tasks/24-guard-tool-output-sequencing-js.md
+++ b/agentydragon/tasks/24-guard-tool-output-sequencing-js.md
@@ -1,10 +1,10 @@
---
+++
 id = "24"
 title = "Guard Against Missing Tool Output in JS Server Sequencing"
 status = "Not started"
 dependencies = "03,06,08,13,15,32,18,19,22,23"
 last_updated = "2025-06-25T01:40:09.600000"
-++
+++

 ## Summary
 Prevent out-of-order chat messages and missing tool outputs when user input interrupts tool execution in the JS backend.
--- a/agentydragon/tasks/25-guard-tool-output-sequencing-rust.md
+++ b/agentydragon/tasks/25-guard-tool-output-sequencing-rust.md
@@ -1,10 +1,10 @@
---
+++
 id = "25"
 title = "Guard Against Missing Tool Output in Rust Server Sequencing"
 status = "Not started"
 dependencies = "03,06,08,13,15,32,18,19,22,23"
 last_updated = "2025-06-25T01:40:09.600000"
-++
+++

 ## Summary
 Prevent out-of-order chat messages and missing tool output errors when user input interrupts tool execution in the Rust backend.
--- a/agentydragon/tasks/26-separate-approval-dialog-from-draft.md
+++ b/agentydragon/tasks/26-separate-approval-dialog-from-draft.md
@@ -1,10 +1,10 @@
---
+++
 id = "26"
 title = "Render Approval Requests in Separate Dialog from Draft Window"
 status = "Not started"
 dependencies = "03,06,08,13,15,32,18,19,22,23"
 last_updated = "2025-06-25T01:40:09.600000"
-++
+++

 ## Summary
 Display patch approval prompts in a distinct dialog or panel to avoid overlaying the draft editor.
--- a/agentydragon/tasks/27-unified-sandbox-retry-prompt-rust.md
+++ b/agentydragon/tasks/27-unified-sandbox-retry-prompt-rust.md
@@ -1,10 +1,10 @@
---
+++
 id = "27"
 title = "Unified Sandbox-Retry Prompt with y/a/A/n Options (Rust)"
 status = "Not started"
 dependencies = "03,06,08,13,15,32,18,19,22,23"
 last_updated = "2025-06-25T01:40:09.600000"
-++
+++

 ## Summary
 Implement a unified retry‑without‑sandbox prompt in the Rust TUI with one‑shot, session‑scoped, and persistent options.
--- a/agentydragon/tasks/28-include-command-snippet-in-approval-label.md
+++ b/agentydragon/tasks/28-include-command-snippet-in-approval-label.md
@@ -1,11 +1,16 @@
---
-id: 28
-title: Include Command Snippet in Session-Scoped Approval Label
-status: Not started  # one of: Not started, Started, Needs manual review, Done, Cancelled
-dependencies: "03,06,08,13,15,32,18,19,22,23"
-summary: When asking for session-scoped approval of a command, embed a truncated snippet of the actual command in the approval label for clarity.
-goal: |
-  Improve the session-scoped approval option label for commands by including a backtick-quoted snippet of the command itself (truncated to fit).  This makes it clear exactly which command (including parameters) will be auto-approved for the session.
+++
+id = "28"
+title = "Include Command Snippet in Session-Scoped Approval Label"
+status = "Not started"
+dependencies = "03,06,08,13,15,32,18,19,22,23"
+last_updated = "2025-06-25T01:40:09.600000"
+++
+
+## Summary
+When asking for session-scoped approval of a command, embed a truncated snippet of the actual command in the approval label for clarity.
+
+## Goal
+Improve the session-scoped approval option label for commands by including a backtick-quoted snippet of the command itself (truncated to fit).  This makes it clear exactly which command (including parameters) will be auto-approved for the session.

 ## Acceptance Criteria

--- a/agentydragon/tasks/29-auto-approve-empty-tool-commands.md
+++ b/agentydragon/tasks/29-auto-approve-empty-tool-commands.md
@@ -1,11 +1,16 @@
---
-id: 29
-title: Auto-Approve Empty-Array Tool Invocations
-status: Not started  # one of: Not started, Started, Needs manual review, Done, Cancelled
-dependencies: "03,06,08,13,15,32,18,19,22,23"
-summary: Automatically approve tool-use requests where the command array is empty, bypassing the approval prompt.
-goal: |
-  In rare cases the model may emit a tool invocation event with an empty `command: []`.  These invocations cannot succeed and continually trigger errors.  Automatically treat empty-array tool requests as approved (once), suppressing the approval UI, to allow downstream error handling rather than perpetual prompts.
+++
+id = "29"
+title = "Auto-Approve Empty-Array Tool Invocations"
+status = "Not started"
+dependencies = "03,06,08,13,15,32,18,19,22,23"
+last_updated = "2025-06-25T01:40:09.600000"
+++
+
+## Summary
+Automatically approve tool-use requests where the command array is empty, bypassing the approval prompt.
+
+## Goal
+In rare cases the model may emit a tool invocation event with an empty `command: []`.  These invocations cannot succeed and continually trigger errors.  Automatically treat empty-array tool requests as approved (once), suppressing the approval UI, to allow downstream error handling rather than perpetual prompts.

 ## Acceptance Criteria

--- a/agentydragon/tasks/30-non-fullscreen-scrollback-mode.md
+++ b/agentydragon/tasks/30-non-fullscreen-scrollback-mode.md
@@ -1,15 +1,20 @@
---
-id: 30
-title: Non-Fullscreen Scrollback Mode with Native Terminal Scroll
-status: Not started  # one of: Not started, Started, Needs manual review, Done, Cancelled
-dependencies: "03,06,08,13,15,32,18,19,22,23"
-summary: Offer a non-fullscreen TUI mode that appends conversation output and defers scrolling to the terminal scrollback.
-goal: |
-  Provide an optional non-fullscreen mode for the chat UI where:
-  - The TUI does not capture the mouse scroll wheel.
-  - All conversation output is appended in place, allowing the terminal's native scrollback to navigate history.
-  - The user-entry window remains fixed at the bottom of the terminal.
-  - The entire UI runs in a standard terminal buffer (no alternate screen), so the user can use their terminal’s scrollbar or scrollback keys to review past messages.
+++
+id = "30"
+title = "Non-Fullscreen Scrollback Mode with Native Terminal Scroll"
+status = "Not started"
+dependencies = "03,06,08,13,15,32,18,19,22,23"
+last_updated = "2025-06-25T01:40:09.600000"
+++
+
+## Summary
+Offer a non-fullscreen TUI mode that appends conversation output and defers scrolling to the terminal scrollback.
+
+## Goal
+Provide an optional non-fullscreen mode for the chat UI where:
+- The TUI does not capture the mouse scroll wheel.
+- All conversation output is appended in place, allowing the terminal's native scrollback to navigate history.
+- The user-entry window remains fixed at the bottom of the terminal.
+- The entire UI runs in a standard terminal buffer (no alternate screen), so the user can use their terminal’s scrollbar or scrollback keys to review past messages.

 ## Acceptance Criteria

--- a/agentydragon/tasks/31-display-context-remaining-percentage.md
+++ b/agentydragon/tasks/31-display-context-remaining-percentage.md
@@ -1,11 +1,16 @@
---
-id: 31
-title: Display Remaining Context Percentage in codex-rs TUI
-status: Not started  # one of: Not started, Started, Needs manual review, Done, Cancelled
-dependencies: "03,06,08,13,15,32,18,19,22,23"
-summary: Show a live "x% context left" indicator in the TUI (Rust) to inform users of remaining model context buffer.
-goal: |
-  Enhance the codex-rs TUI by adding a status indicator that displays the percentage of model context buffer remaining (e.g. "75% context left").  Update this indicator dynamically as the conversation progresses.
+++
+id = "31"
+title = "Display Remaining Context Percentage in codex-rs TUI"
+status = "Not started"
+dependencies = "03,06,08,13,15,32,18,19,22,23"
+last_updated = "2025-06-25T01:40:09.600000"
+++
+
+## Summary
+Show a live "x% context left" indicator in the TUI (Rust) to inform users of remaining model context buffer.
+
+## Goal
+Enhance the codex-rs TUI by adding a status indicator that displays the percentage of model context buffer remaining (e.g. "75% context left").  Update this indicator dynamically as the conversation progresses.

 ## Acceptance Criteria

--- a/agentydragon/tasks/task-template.md
+++ b/agentydragon/tasks/task-template.md
@@ -1,18 +1,18 @@
-# Task Template
-
-# Valid status values: Not started | Started | Needs manual review | Done | Cancelled
-
---
---
+++
 id = "<NN>"
 title = "<Task Title>"
-status = "<<<!!! MANAGER: SET VALID STATUS !!!>>>"
+status = "<<<!!! MANAGER: SET VALID STATUS  - Not started? !!!>>>"
 summary = "Brief summary of current status."
 dependencies = "<<<!!! MANAGER: POPULATE THIS WHEN CREATING TASK !!!>>>"
 last_updated = "<timestamp in ISO format>"
 goal: |
  Describe the objective of the task here.
---
+++
+
+# Task Template
+
+# Valid status values: Not started | Started | Needs manual review | Done | Cancelled
+

 > *This task is specific to codex-rs.*