dscli-agent 0.4.0__tar.gz → 0.6.0__tar.gz

{dscli_agent-0.4.0/dscli_agent.egg-info → dscli_agent-0.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dscli-agent
-Version: 0.4.0
+Version: 0.6.0
 Summary: A local coding agent that uses DeepSeek web chat as its model
 Author: Anish
 License-Expression: MIT
@@ -106,11 +106,33 @@ dscli
 
 dscli shows an inline terminal UI inspired by Claude Code: a cleared screen and gradient
 ASCII wordmark on launch, an animated spinner with rotating status verbs, a smoothly
-revealed streaming answer, compact tool cards (`⏺ Read(...)`, `⏺ Update(...)`,
-`⏺ Run(...)`), colored diffs for approvals, and the final answer rendered as Markdown.
+revealed streaming answer, tree-style tool cards, approval prompts that name the action
+and path without printing file contents, and the final answer rendered as Markdown.
+
+Each tool call renders as a card with a short result summary and, when there is more to
+see, a preview of the output:
+
+```text
+ ▪ Read(dscli/config.py · lines 1-40)
+   └ Read lines 1-40 of 120 (Ctrl+O to expand)
+
+ ▪ Edit(dscli/config.py)
+   └ Accepted config.py (Ctrl+O to expand)
+
+ ▪ Bash(grep -n "read_file" dscli/prompts.py)
+   └ 121:- Do NOT use read_file, write_file, apply_patch, list_files...
+     243:  non-empty plan. Start by investigating with read_file and list_files
+     … +2 lines (Ctrl+O to expand)
+```
+
+Failed calls keep the `▪` header and show the error under the `└` branch. Long paths are
+shortened in the middle and long commands are trimmed to keep the card on one line.
+Press `Ctrl+O` at the prompt to print the full output of the most recent tool card or
+thinking block.
 Accents use a muted palette that matches the wordmark: sage for success, dusty rose for
-errors, and soft teal for diffs and highlights. The same muted colors apply to the
-plain and non-TTY output.
+errors, and soft teal for highlights. Markdown answers — streamed, interrupted, and
+final — use the same palette for headings, links, inline code, and fenced code
+highlighting. The same muted colors apply to the plain and non-TTY output.
 Output stays in normal scrollback after startup; dscli does not take over the full
 screen, and the welcome card shows the workspace, model, active modes, and shortcuts.
 Plans
@@ -132,12 +154,12 @@ DeepThink is always enabled, and the UI streams the model's reasoning live in a
 compact block above the reply:
 
 ```text
-  Thinking
-  │ I should inspect the configuration first.
-  │ … +12 rows (Ctrl+O)
-  │ charlie line
-  │ delta line
-  │ echo line
+ Thinking
+ │ I should inspect the configuration first.
+ │ … +12 rows (Ctrl+O to expand)
+ │ charlie line
+ │ delta line
+ │ echo line
 ```
 
 The first sentence stays pinned at the top while the newest three wrapped rows
@@ -147,11 +169,11 @@ it collapses to the same limited view with a `Ctrl+O` hint; press `Ctrl+O` at th
 prompt to print the full reasoning block (up to 500 rows) into the transcript.
 The streamed block is TUI-only; `--plain` and `run` do not show it.
 
-The prompt footer tracks session token usage against a 1,000,000-token budget, and the
-same progress bar renders below the live Thinking and Responding output:
+The prompt footer tracks the session's context volume against a 1,000,000-token budget,
+and the same progress bar renders below the live Thinking and Responding output:
 
 ```text
-  tokens ███████░░░░░ 612.4k / 1.0M · 61%
+  context ███████░░░░░ 612.4k / 1.0M · 61%
 ```
 
 Counts are estimated locally from every prompt sent and reply received (one token per
@@ -161,7 +183,7 @@ a new chat is opened.
 
 ### Conversation compaction
 
-When the estimate reaches 1,000,000 tokens, dscli compacts the session instead of
+When the count reaches 1,000,000 tokens, dscli compacts the session instead of
 stopping. Before the next prompt is sent it asks the current chat to write a structured
 compaction summary — an `<analysis>` pass followed by a `<summary>` covering the request,
 technical decisions, files and code, errors and fixes, user messages, pending tasks, and
@@ -179,9 +201,14 @@ Files are saved under `%APPDATA%\dscli\compactions` on Windows
 `~/.config/dscli/compactions` elsewhere) as `compaction-YYYYmmdd-HHMMSS.txt`. The check
 runs before every model turn, so it also works mid-task; the TUI shows a
 `Compacting conversation` spinner while the summary is written, then a
-`⟳ Compacted 1.0M tokens → … · new chat` notice. `/new` clears the recorded
+`⟳ Compacted context at 1.0M tokens → … · new chat` notice. `/new` clears the recorded
 conversation as well.
 
+Type `/compact` in `dscli chat` to compact on demand. dscli asks the current chat for the
+summary, writes the compaction file, and starts a new DeepSeek chat; the next message you
+send resumes the compacted conversation there, with the compaction attached. `/compact`
+needs at least one earlier message, and `/new` discards a pending compaction.
+
 ### Deeplanning mode
 
 ```powershell
@@ -208,14 +235,15 @@ every run with `dscli config --set deeplanning=true`, or turn it off for one run
 | `Ctrl+C` | While the agent is working: interrupt the current turn, keep the browser session, and return to the prompt. At the prompt: clear the input. |
 | `Ctrl+D` | Exit dscli. |
 | `↑` / `↓` | Browse previous messages. |
-| `Ctrl+O` | Expand the last thinking block in full. |
+| `Ctrl+O` | Expand the last thinking block or tool output in full. |
 
 Typing `/` opens an autocomplete menu. History is saved to
 `%APPDATA%\dscli\chat_history` (`~/Library/Application Support/dscli/chat_history` on
 macOS, `~/.config/dscli/chat_history` elsewhere).
 
-Slash commands: `/help` lists commands and shortcuts, `/new` starts a fresh
-conversation so the agent forgets earlier turns, and `/exit` (or `/quit`) closes dscli.
+Slash commands: `/help` lists commands and shortcuts, `/compact` summarizes the
+conversation and continues it in a new chat, `/new` starts a fresh conversation so the
+agent forgets earlier turns, and `/exit` (or `/quit`) closes dscli.
 
 If Cloudflare interrupts a headless run, dscli opens the persistent profile in a visible
 Chrome window and resubmits the interrupted prompt. Complete the check in that window.
@@ -225,8 +253,8 @@ current model turn restarts with the same prompt in a fresh chat, so an answer t
 already streaming when the check appeared is fetched again. Set
 `dscli config --set auto_human_check=false` to fail fast instead.
 
-When dscli asks to write a file or run a command, it shows the title and a compact
-colored diff (additions green, deletions red, hunks cyan) even when `-y` is active.
+When dscli asks to write a file or run a command, it shows the title and, for commands,
+the exact command. File contents and diffs are never printed.
 Answer `y` to approve once, `n` to deny, `a` to approve everything for the rest of the
 session, or `q` to quit.
 
@@ -269,7 +297,7 @@ dscli run --prompt-file task.md -y
 dscli run "Review the docs" --no-shell
 ```
 
-The final answer is printed to stdout. Progress, diffs, and approval prompts go to
+The final answer is printed to stdout. Progress and approval prompts go to
 stderr, so `dscli run ... > result.txt` captures only the answer. `run` never uses the
 interactive UI; its output contract is unchanged.
 
@@ -289,7 +317,7 @@ failures and unconfirmed completions are always logged to stderr, including unde
 | `--headed` / `--headless` | Show or hide the browser. Headless is the default. |
 | `--search` | Turn DeepSeek's Search mode on for the run (DeepThink is always on). |
 | `--deeplanning` | Require a non-empty `update_plan` before writes or commands (alias: `--deep-planning`). |
-| `--max-steps N` | Maximum model turns (default 12). |
+| `--max-steps N` | Maximum model turns (default 20, cap 150). |
 | `--timeout N` | Response timeout per turn in seconds (default 300). |
 | `--verify CMD` | Run CMD automatically after file edits; failures block success. |
 | `--no-verify` | Disable the configured `verify_command` for this run. |
@@ -357,6 +385,7 @@ creep and unnecessary abstractions, confirm hard-to-reverse actions, reference c
 | `write_file` | **Create** a new file. Refuses to overwrite an existing non-empty file. |
 | `apply_patch` | The only way to edit an existing file: exact `search` → `replace`. |
 | `list_files` | Bounded recursive listing. |
+| `search_files` | Search text files for a literal string; returns `path:line` matches. |
 | `delete_file` | Delete one file when explicitly requested (approval required). |
 | `run_command` | Run a command with an approval prompt via PowerShell, cmd.exe, sh, or bash. |
 | `update_plan` | Create or revise the task plan; the task cannot finish while steps are unfinished. |
@@ -404,8 +433,9 @@ model can modify the files it checks, so review the final diff.
 
 - Tools are confined to the workspace unless `--allow-outside` is passed.
 - `.git` is never writable through the tools.
-- Every write, patch, delete, and command shows a diff/command and asks
-  `[y]es / [n]o / [a]ll / [q]uit` before changing anything. `-y` skips the prompts.
+- Every write, patch, delete, and command shows the action and affected path (or the
+  exact command) and asks `[y]es / [n]o / [a]ll / [q]uit` before changing anything.
+  File contents and diffs are never printed. `-y` skips the prompts.
 - Command execution is enabled by default, but every model-requested command still
   requires approval. The prompt names the interpreter (PowerShell, cmd.exe, sh, or
   bash). `--no-shell` disables model-requested commands for a run.
@@ -420,7 +450,8 @@ model can modify the files it checks, so review the final diff.
   through the browser.
 
 This is still an assistant with write access to your files. Use a clean workspace or
-version control, and review diffs before approving them.
+version control, and review the changes in your VCS after a run; approval prompts show
+only the action and path, not the file contents.
 
 ## Configuration
 
@@ -439,7 +470,9 @@ Useful keys: `url` (the DeepSeek chat URL; set it only for a custom deployment),
 import), `chrome_profile` (empty = Chrome's last-used profile, or a name such as
 `Default` / `Profile 1`), `user_agent` (empty = derive a normal Chrome UA from the
 installed browser), `response_timeout_sec`, `first_response_timeout_sec`,
-`stable_seconds`, `fallback_stable_seconds`, `auto_human_check` (true = open a visible
+`stable_seconds`, `fallback_stable_seconds`, `activity_settle_seconds` (how long the
+page must stay free of DOM mutations before a reply counts as finished; default 1.5),
+`auto_human_check` (true = open a visible
 window to solve a verification check; false = fail fast), `max_steps`, `max_tool_calls`,
 `max_read_chars`, `max_attachment_mb`, `search`, `deeplanning`, `shell_enabled`
 (default true; every command still requires approval), `allow_outside`,
@@ -502,10 +535,11 @@ profile.
 may exceed the chat's limit, or the selector may have changed. Run `doctor` and check
 the reported counts.
 
-**A response is cut off around 12 s after the last text change.** DeepSeek did not
-show its completion toolbar (`Read aloud`), so dscli used the fallback completion
-detector. Increase `fallback_stable_seconds` if replies are still streaming at that
-point.
+**A response is cut off around 12 s after the last text change.** dscli normally waits
+for the reply text to stabilize while the page itself stops changing DOM nodes and
+text (`activity_settle_seconds`, default 1.5 s). If the page keeps mutating, the
+fallback detector returns the reply after `fallback_stable_seconds` of text stability.
+Increase `fallback_stable_seconds` if replies are still streaming at that point.
 
 **Chrome will not launch.** Set `"channel": ""` in the config to use Playwright's
 Chromium, after running `python -m playwright install chromium`.
@@ -522,7 +556,7 @@ Debug screenshots and unparsed replies are written to `%APPDATA%\dscli\debug`.
 - Streaming is approximated by polling the DOM, not by tokens from the model. The
   interactive chat streams a final answer as the page updates only after it declares
   `complete: true`; tool calls still wait for the complete, validated JSON envelope.
-  The token bar is likewise a local estimate of sent and received text, not usage
+  The context bar is likewise a local estimate of sent and received text, not usage
   reported by DeepSeek.
 - Interrupting with Ctrl+C clicks DeepSeek's labelled stop button when dscli can find
   it. If the page does not expose one, generation may continue in the web chat; the