dscli-agent 0.5.0__tar.gz → 0.6.0__tar.gz

{dscli_agent-0.5.0 → dscli_agent-0.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dscli-agent
-Version: 0.5.0
+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
@@ -182,6 +204,11 @@ runs before every model turn, so it also works mid-task; the TUI shows a
 `⟳ 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
 

{dscli_agent-0.5.0 → dscli_agent-0.6.0}/README.md

@@ -76,11 +76,33 @@ 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
@@ -102,12 +124,12 @@ 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
@@ -152,6 +174,11 @@ runs before every model turn, so it also works mid-task; the TUI shows a
 `⟳ 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
@@ -178,14 +205,15 @@ 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.
@@ -195,8 +223,8 @@ 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.
 
@@ -239,7 +267,7 @@ 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.
 
@@ -259,7 +287,7 @@ 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. |
@@ -327,6 +355,7 @@ 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. |
@@ -374,8 +403,9 @@ 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.
@@ -390,7 +420,8 @@ 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
 

{dscli_agent-0.5.0 → dscli_agent-0.6.0}/dscli/__init__.py

@@ -1,3 +1,3 @@
 """dscli - a local coding agent for your terminal."""
 
-__version__ = "0.5.0"
+__version__ = "0.6.0"

{dscli_agent-0.5.0 → dscli_agent-0.6.0}/dscli/agent.py

@@ -10,7 +10,12 @@ from typing import Callable
 
 from .attachments import Attachment
 from .browser import ChatSession
-from .compaction import ConversationLog, extract_compact_summary, write_compaction
+from .compaction import (
+    Compaction,
+    ConversationLog,
+    extract_compact_summary,
+    write_compaction,
+)
 from .config import Config
 from .display import AgentDisplay, PlainDisplay
 from .prompts import (
@@ -59,6 +64,73 @@ class AgentOutcome:
     completed: bool = False
 
 
+def request_compaction_summary(
+    *,
+    session: ChatSession,
+    display: AgentDisplay,
+    task: str,
+    plan: list[PlanStep] | None,
+    changed: list[str],
+    manual: bool = False,
+) -> str:
+    display.compaction_summarizing()
+    prompt = build_compact_prompt(
+        task=task,
+        plan=plan,
+        changed=changed,
+        manual=manual,
+    )
+    try:
+        reply = session.send_and_wait(prompt)
+    except Exception as exc:
+        log.warning("Could not request a compaction summary: %s", exc)
+        return ""
+    summary = extract_compact_summary(reply)
+    if not summary:
+        log.warning(
+            "The model's compaction summary was empty or unreadable; "
+            "using the activity log only."
+        )
+    return summary
+
+
+def compact_conversation(
+    *,
+    session: ChatSession,
+    toolbox: Toolbox,
+    workspace: Path,
+    task: str,
+    history: ConversationLog,
+    display: AgentDisplay,
+    verification: str = "",
+) -> Compaction:
+    """Summarize the chat, write the compaction file, and open a new chat."""
+    summary = request_compaction_summary(
+        session=session,
+        display=display,
+        task=task,
+        plan=toolbox.plan,
+        changed=toolbox.changed_files,
+        manual=True,
+    )
+    used = int(getattr(session, "context_tokens", 0) or 0)
+    compaction = write_compaction(
+        workspace=workspace,
+        task=task,
+        log=history,
+        plan=toolbox.plan,
+        changed=toolbox.changed_files,
+        verification=verification,
+        context_tokens=used,
+        project_tree=project_structure(workspace),
+        summary=summary,
+    )
+    session.new_chat()
+    session.set_modes()
+    display.compaction_started(str(compaction.path), used)
+    return compaction
+
+
 class Agent:
     def __init__(
         self,
@@ -76,6 +148,7 @@ class Agent:
         on_thinking_snapshot: Callable[[str], None] | None = None,
         display: AgentDisplay | None = None,
         history: ConversationLog | None = None,
+        resume: Compaction | None = None,
     ) -> None:
         self.session = session
         self.cfg = config
@@ -85,6 +158,7 @@ class Agent:
         self.attachments = attachments
         self.verbose = verbose
         self.followup = followup
+        self.resume = resume
         self.on_final_snapshot = on_final_snapshot
         self.on_thinking_snapshot = on_thinking_snapshot
         self.display = display or PlainDisplay(
@@ -120,24 +194,13 @@ class Agent:
         return self._verify_command or "(none configured)"
 
     def _request_compaction_summary(self, plan: list[PlanStep] | None) -> str:
-        self.display.compaction_summarizing()
-        prompt = build_compact_prompt(
+        return request_compaction_summary(
+            session=self.session,
+            display=self.display,
             task=self.task,
             plan=plan,
             changed=self.toolbox.changed_files,
         )
-        try:
-            reply = self.session.send_and_wait(prompt)
-        except Exception as exc:
-            log.warning("Could not request a compaction summary: %s", exc)
-            return ""
-        summary = extract_compact_summary(reply)
-        if not summary:
-            log.warning(
-                "The model's compaction summary was empty or unreadable; "
-                "using the activity log only."
-            )
-        return summary
 
     def _prepare_send(
         self,
@@ -285,7 +348,30 @@ class Agent:
         self._sent_any = False
         self.history.add_task(self.task)
 
-        if self.followup:
+        if self.resume is not None:
+            self.history.add_note(
+                f"Resumed from {self.resume.path.name} in a new chat."
+            )
+            initial = build_resume_prompt(
+                task=self.task,
+                workspace=self.workspace,
+                compaction=self.resume.text,
+                workspace_tree=workspace_preview(self.workspace),
+                plan=self.toolbox.plan,
+                live_plan=self.toolbox.plan,
+                changed=self.toolbox.changed_files,
+                attachments=self.attachments,
+                allow_shell=self.cfg.shell_enabled,
+                allow_outside=self.cfg.allow_outside,
+                max_steps=self.cfg.max_steps,
+                verify_command=self._verify_command,
+                compaction_name=self.resume.path.name,
+                deeplanning=self.cfg.deeplanning,
+                max_tool_calls=self.cfg.max_tool_calls,
+                turn_id=self.turn_id,
+                manual=True,
+            )
+        elif self.followup:
             initial = build_followup_prompt(
                 self.task,
                 turn_id=self.turn_id,
@@ -314,10 +400,11 @@ class Agent:
             )
 
         attachment_paths = [a.path for a in self.attachments]
+        if self.resume is not None:
+            attachment_paths.insert(0, self.resume.path)
         message = initial
         files = attachment_paths if attachment_paths else None
         turn = 0
-        protocol_failures = 0
         last_reply = ""
 
         while True:
@@ -342,13 +429,7 @@ class Agent:
             try:
                 step = parse_step(last_reply)
             except ProtocolError as exc:
-                protocol_failures += 1
                 self.session.save_last_response(last_reply, "protocol-error")
-                if protocol_failures > self.cfg.max_protocol_retries:
-                    raise ProtocolError(
-                        f"{exc} The raw reply was saved to the dscli debug directory.",
-                        last_reply,
-                    ) from exc
                 self.display.protocol_error(str(exc))
                 if turn >= self.cfg.max_steps:
                     return self._wrap_up(turn, last_reply or str(exc))
@@ -363,13 +444,7 @@ class Agent:
 
             turn_error = self._turn_id_error(step)
             if turn_error is not None:
-                protocol_failures += 1
                 self.session.save_last_response(last_reply, "turn-id-error")
-                if protocol_failures > self.cfg.max_protocol_retries:
-                    raise ProtocolError(
-                        f"{turn_error} The raw reply was saved to the dscli debug directory.",
-                        last_reply,
-                    )
                 self.display.protocol_error(turn_error)
                 if turn >= self.cfg.max_steps:
                     return self._wrap_up(turn, last_reply)
@@ -413,14 +488,11 @@ class Agent:
 
             if not step.tool_calls:
                 # Should have been caught by the parser; treat it as a protocol miss.
-                protocol_failures += 1
-                if protocol_failures > self.cfg.max_protocol_retries:
-                    raise ProtocolError(
-                        "The model returned an envelope with no tool calls and no final answer.",
-                        last_reply,
-                    )
                 if turn >= self.cfg.max_steps:
                     return self._wrap_up(turn, last_reply)
+                self.display.protocol_error(
+                    "The envelope had neither tool_calls nor final."
+                )
                 message = build_protocol_repair(
                     "The envelope had neither tool_calls nor final.",
                     task=self.task,
@@ -701,6 +773,7 @@ def run_agent(
     on_thinking_snapshot: Callable[[str], None] | None = None,
     display: AgentDisplay | None = None,
     history: ConversationLog | None = None,
+    resume: Compaction | None = None,
 ) -> AgentOutcome:
     return Agent(
         session=session,
@@ -716,4 +789,5 @@ def run_agent(
         on_thinking_snapshot=on_thinking_snapshot,
         display=display,
         history=history,
+        resume=resume,
     ).run()