PyModel
diff --git a/‎CHANGELOG.md‎
Lines changed: 10 additions & 0 deletions b/‎CHANGELOG.md‎
Lines changed: 10 additions & 0 deletions
diff --git a/‎docs/en/customization/architecture.md‎
Lines changed: 1 addition & 1 deletion b/‎docs/en/customization/architecture.md‎
Lines changed: 1 addition & 1 deletion
diff --git a/‎scripts/build_vis.py‎
Lines changed: 2 additions & 2 deletions b/‎scripts/build_vis.py‎
Lines changed: 2 additions & 2 deletions
diff --git a/‎src/pythinker_code/agents/default/system.md‎
Lines changed: 2 additions & 2 deletions b/‎src/pythinker_code/agents/default/system.md‎
Lines changed: 2 additions & 2 deletions
diff --git a/‎src/pythinker_code/app.py‎
Lines changed: 8 additions & 0 deletions b/‎src/pythinker_code/app.py‎
Lines changed: 8 additions & 0 deletions
diff --git a/‎src/pythinker_code/cli/__init__.py‎
Lines changed: 17 additions & 1 deletion b/‎src/pythinker_code/cli/__init__.py‎
Lines changed: 17 additions & 1 deletion
diff --git a/‎src/pythinker_code/config.py‎
Lines changed: 8 additions & 0 deletions b/‎src/pythinker_code/config.py‎
Lines changed: 8 additions & 0 deletions
diff --git a/‎src/pythinker_code/project_memory.py‎
Lines changed: 101 additions & 17 deletions b/‎src/pythinker_code/project_memory.py‎
Lines changed: 101 additions & 17 deletions
@@ -15,6 +15,16 @@ GitHub Releases page; `0.8.0` is the new starting line.
 
 ## Unreleased
 
+- **designer-skill MCP bridge.** Bundled a `designer-skill` stub skill that routes frontend work to the connected designer-skill MCP tools instead of failing ReadSkill; plugin-style names like `designer-skill:designer-skill` resolve correctly, and ReadSkill falls back to a generic MCP bridge (any user-configured server name) when only the MCP server is connected.
+- **Always-on best practices.** New `best_practices_always` config option folds the full `/best-practices` engineering guidance into the root session's system prompt at startup, so the guardrails apply to every new session without running the command. Default off.
+- **Smarter multi-edit errors.** A `StrReplaceFile` batch that fails schema validation (e.g. edit entries collapsed by a streaming glitch) now returns a precise, actionable error naming the bad entries and steering toward single-edit calls, instead of a wall of validation errors. Valid edits are never partially applied.
+- **Agent guardrails.** The default system prompt now requires absence claims ("no em-dashes", "no leftover debug", "matches the source") to be backed by an actual zero-hit scan, and to re-ask rather than act on a self-authored reading of a non-responsive clarifying answer.
+- **`/recap on|off`.** Toggle turn recaps from the recap command (mirrors `/settings recap(s)`), with a grey inline autosuggest reflecting the current state.
+- **Recap hygiene.** Session recaps strip `<system-reminder>` blocks so injected harness context no longer leaks into one-line recaps.
+- **Login selector polish.** Configured `/login` providers render with distinct success/state styling; the background working indicator uses the braille spinner, and working tips wrap with a hanging indent under the verb.
+- **Scratch cleanup on exit.** Sessions that end via an exception now clean up their scratch files instead of orphaning them.
+- **Readable diff context.** Unchanged context lines in file-edit diff snippets now render in the normal body-text color instead of muted grey, so edited-file previews are easier to read; added/removed lines are unchanged.
+
 ## 0.42.0 (2026-06-12)
 
 - **Adversarial branch review hardening.** A multi-agent review pass confirmed and fixed: committed-but-clean isolation worktrees are now retained (commits ahead of the creation base count as changes — they were previously orphaned on cleanup); foreground shell commands and relative-path file edits now resolve against the agent's work dir, so worktree isolation actually binds them (host exec gained a `cwd` argument); safe mode now also disables the read-only-command prompt elision; locally parallel-safe MCP/tools run in parallel in the same-step gate; worktree add/remove serializes per repo. Behavior notes: same-step tool calls without `supports_parallel` now serialize deterministically (previously fully concurrent), and text-mode error diagnostics moved to stderr — capture `2>&1` or use `--output-format stream-json` if you scraped stdout.
 
@@ -219,7 +219,7 @@ is load-bearing for approval gating of persistent-backdoor vectors (`AGENTS.md`,
 | --- | --- | --- |
 | `src/pythinker_code/web/` | FastAPI backend (port 5494) managing CLI sessions via subprocess workers; bearer-token auth; `/api/*`; sensitive-path restriction. | `create_app`, `run_web_server`, `PythinkerCLIRunner`, `SessionProcess`, `AuthMiddleware` |
 | `src/pythinker_code/vis/` | FastAPI read-only tracing/statistics backend (port 5495) for the visualizer. | `create_app`, `run_vis_server` |
-| `web/` | React 19 + Vite 7 + TypeScript SPA chat UI; bundled into the package. See `web/AGENTS.md`. | `main.tsx`, `App`, `apiClient`, generated client `src/lib/api/`, `useSessionStream` |
+| `web/` | React 19 + Vite 8 + TypeScript SPA chat UI; bundled into the package. See `web/AGENTS.md`. | `main.tsx`, `App`, `apiClient`, generated client `src/lib/api/`, `useSessionStream` |
 | `vis/` | React 19 + Vite session-tracing visualizer. See `vis/AGENTS.md`. | `main.tsx`, `App`, hand-written `src/lib/api.ts` (`WireEvent`, `ContextMessage`, `SessionInfo`), feature panels under `src/features/` |
 
 Both frontends build with `tsc -b && vite build` and are synced into the Python package by
 
@@ -35,7 +35,7 @@ def resolve_npm() -> str | None:
 
 
 def check_node_version() -> bool:
-    """Vite 7 requires Node.js ^20.19.0 || >=22.12.0."""
+    """Vite 8 requires Node.js ^20.19.0 || >=22.12.0."""
     node = shutil.which("node")
     if not node:
         return False
@@ -47,7 +47,7 @@ def check_node_version() -> bool:
         ok = (major == 20 and minor >= 19) or (major >= 22 and (major > 22 or minor >= 12))
         if not ok:
             print(
-                f"Node.js ^20.19.0 or >=22.12.0 required (Vite 7), found v{version}",
+                f"Node.js ^20.19.0 or >=22.12.0 required (Vite 8), found v{version}",
                 file=sys.stderr,
             )
             return False
 
@@ -23,7 +23,7 @@ Eight rules that override convenience, speed, and every other instruction in thi
 
 1. **Read before write.** Never edit a file you have not read this session; confirm the exact lines you are about to modify still match what you read.
 2. **Complete code only.** Never write placeholders, stubs, `TODO: implement`, elided bodies, or "rest of the file unchanged" markers into files. If a change is too large for one step, split the work — never abridge the code. (Genuine `TODO:` notes for real technical debt are fine.)
-3. **Evidence before claims.** Every "done", "fixed", or "works" names the command you ran and the result you observed. Verification means a passing test, a working repro, or a deterministic command that confirms the intended behavior — compiling or type-checking alone is not verification. This definition is canonical: it is what "verify" means everywhere in this prompt.
+3. **Evidence before claims.** Every "done", "fixed", or "works" names the command you ran and the result you observed. Verification means a passing test, a working repro, or a deterministic command that confirms the intended behavior — compiling or type-checking alone is not verification. This definition is canonical: it is what "verify" means everywhere in this prompt. A claim that something is *absent* — no banned strings, no em-dashes, no leftover debug instrumentation, no TODOs, output matches the source — is only true after a scan that returned zero hits; never assert absence from memory.
 4. **Re-verify after every edit.** An edit invalidates all prior verification; re-run the smallest check that proves the change is sound before building on top of it.
 5. **Honest failure.** When verification fails, report the failing output verbatim under **BLOCKERS**. Never weaken an assertion, skip a test, widen a tolerance, swallow an error, or silently narrow scope to get to green.
 6. **Match the codebase.** Existing style, granularity, naming, and idioms beat your preferences. A correct change that fights the codebase's conventions is not done.
@@ -57,7 +57,7 @@ State multi-step plans inline as `Step → verify: check`; substantial tasks kee
 
 **Report** with `path:line` references over pasted blocks, concise findings, and explicit residual risk — unverified assumptions, untested paths, recommended follow-ups, and unrelated issues noticed but not touched.
 
-**Ask vs. act.** Act without asking when intent is clear, the change is reversible, and it is in scope. Ask one focused question — before implementation, never after mistakes — when interpretations genuinely diverge, an action is irreversible or destructive, credentials are needed, requirements conflict, or scope grows beyond the request. Never ask what a tool call can answer.
+**Ask vs. act.** Act without asking when intent is clear, the change is reversible, and it is in scope. Ask one focused question — before implementation, never after mistakes — when interpretations genuinely diverge, an action is irreversible or destructive, credentials are needed, requirements conflict, or scope grows beyond the request. Never ask what a tool call can answer. If an answer to a clarifying question does not actually resolve the ambiguity, say so and re-ask with your default stated — never act on a self-authored interpretation of a non-answer.
 
 **Steering.** If the user interjects or redirects mid-task, stop, reconcile the new instruction with the current plan, update the todos, then continue.
 
 
@@ -352,6 +352,14 @@ async def create(
         )
         _phase_timings_ms["mcp_ms"] = int((time.monotonic() - _phase_t) * 1000)
 
+        if runtime.config.best_practices_always:
+            from pythinker_code.prompts import apply_always_on_best_practices
+
+            agent = dataclasses.replace(
+                agent,
+                system_prompt=apply_always_on_best_practices(agent.system_prompt, enabled=True),
+            )
+
         if startup_progress is not None:
             startup_progress("Restoring conversation...")
         context = Context(session.context_file)
 
@@ -1203,10 +1203,26 @@ async def _reload_loop(session_id: str | None) -> tuple[str | None, int]:
             # the most recent _run() call, which may have failed before returning.
             # last_session is from a *previous* iteration and must not be touched.
             if _latest_created_session is not None:
+                try:
+                    from pythinker_code.scratchpad import cleanup_session_scratch
+
+                    await cleanup_session_scratch(
+                        _latest_created_session.work_dir,
+                        session_id=_latest_created_session.id,
+                        session_title=_latest_created_session.title,
+                    )
+                except Exception:
+                    # Best-effort cleanup: log at debug so the failure is traceable
+                    # without disrupting the exception currently being re-raised.
+                    logger.opt(exception=True).debug(
+                        "Best-effort exception-path scratch cleanup failed"
+                    )
                 _print_resume_hint(_latest_created_session)
                 if _latest_created_session.is_empty():
-                    with contextlib.suppress(Exception):
+                    try:
                         await _delete_empty_session(_latest_created_session)
+                    except Exception:
+                        logger.opt(exception=True).debug("Best-effort empty-session cleanup failed")
             raise
 
     if _picker_mode:
 
@@ -1020,6 +1020,14 @@ class Config(BaseModel):
         ),
     )
     default_yolo: bool = Field(default=False, description="Default yolo (auto-approve) mode")
+    best_practices_always: bool = Field(
+        default=False,
+        description=(
+            "When true, fold the full /best-practices engineering guidance into the root "
+            "session's system prompt at startup, so the guardrails apply without running "
+            "/best-practices manually. Applies to new sessions; costs context tokens each session."
+        ),
+    )
     ask_user_question_policy: Literal["always", "ask_except_auto", "never", "auto_deliberate"] = (
         Field(
             default="ask_except_auto",
 
@@ -35,8 +35,8 @@
     from pythinker_code.soul.pythinkersoul import PythinkerSoul
 
 ENTRY_DELIMITER = "\n§\n"
-MEMORY_CHAR_LIMIT = 2200
-USER_CHAR_LIMIT = 1375
+MEMORY_CHAR_LIMIT = 5000
+USER_CHAR_LIMIT = 2500
 INJECTION_BUDGET_BYTES = 8 * 1024
 _JOURNAL_MAX_ENTRIES = 100
 
@@ -92,6 +92,9 @@ async def project_key(work_dir: HostPath, *, git_runner: GitRunner | None = None
 class MemoryOpResult:
     ok: bool
     message: str
+    # True only when the op failed because the store is at capacity. Lets the UI
+    # layer attach user-facing guidance without string-matching the message.
+    full: bool = False
 
 
 class ProjectMemoryStore:
@@ -130,6 +133,31 @@ def _filename(self, target: Target) -> str:
     def _char_limit(self, target: Target) -> int:
         return self._user_limit if target == "user" else self._memory_limit
 
+    @staticmethod
+    def _used(entries: list[str]) -> int:
+        return len(ENTRY_DELIMITER.join(entries))
+
+    @staticmethod
+    def _append_overhead(entries: list[str]) -> int:
+        """Chars an appended entry costs beyond its own text (the joining delimiter)."""
+        return len(ENTRY_DELIMITER) if entries else 0
+
+    @staticmethod
+    def _inventory(entries: list[str]) -> str:
+        """Compact, model-readable listing: index, size, and a one-line preview.
+
+        The preview doubles as a copy-paste ``old_text`` substring for remove/replace,
+        turning a space-rejection into a guided one-step fix instead of a guessing game.
+        """
+        if not entries:
+            return "  (none)"
+        lines: list[str] = []
+        for i, entry in enumerate(entries):
+            preview = " ".join(entry.split())
+            clipped = preview[:60] + ("…" if len(preview) > 60 else "")
+            lines.append(f"  [{i}] {len(entry)} chars — {clipped}")
+        return "\n".join(lines)
+
     async def _path_for(self, target: Target) -> Path:
         root = await self._ensure_dir()
         return root / "memory" / self._filename(target)
@@ -219,13 +247,19 @@ async def add(self, target: Target, content: str) -> MemoryOpResult:
             if content in entries:
                 return MemoryOpResult(True, "Entry already exists (no duplicate added).")
             limit = self._char_limit(target)
-            new_total = len(ENTRY_DELIMITER.join([*entries, content]))
-            if new_total > limit:
-                current = len(ENTRY_DELIMITER.join(entries))
+            if len(ENTRY_DELIMITER.join([*entries, content])) > limit:
+                used = self._used(entries)
+                overhead = self._append_overhead(entries)
+                free = max(0, limit - used - overhead)
+                need = len(content) + overhead
                 return MemoryOpResult(
                     False,
-                    f"Memory at {current}/{limit} chars; this entry ({len(content)}) "
-                    "exceeds the limit. Replace or remove entries first.",
+                    f"Not enough room: this entry needs {need} chars "
+                    f"(content {len(content)} + {overhead} separator), but only {free} free "
+                    f"({used}/{limit} used). Remove or replace an entry to free space, "
+                    f"or shorten this entry to ≤{free} chars.\n"
+                    f"Current entries:\n{self._inventory(entries)}",
+                    full=True,
                 )
             await self._write_entries(target, [*entries, content])
         return MemoryOpResult(True, "Entry added.")
@@ -241,11 +275,28 @@ def _match_one(entries: list[str], old_text: str) -> int | MemoryOpResult:
             )
         return matches[0]
 
-    async def replace(self, target: Target, old_text: str, new_content: str) -> MemoryOpResult:
+    def _locate(self, entries: list[str], old_text: str, index: int | None) -> int | MemoryOpResult:
+        """Resolve which entry to mutate. ``index`` (0-based, from `list`) is the
+        deterministic path — preferred when substring matching is uncertain;
+        ``old_text`` is the substring fallback. Out-of-range indices report the
+        inventory so the retry is guided, not a guess."""
+        if index is not None:
+            if not 0 <= index < len(entries):
+                return MemoryOpResult(
+                    False,
+                    f"No entry at index {index} ({len(entries)} stored). "
+                    f"Current entries:\n{self._inventory(entries)}",
+                )
+            return index
+        if old_text:
+            return self._match_one(entries, old_text)
+        return MemoryOpResult(False, "Provide old_text or index to identify the entry.")
+
+    async def replace(
+        self, target: Target, old_text: str, new_content: str, *, index: int | None = None
+    ) -> MemoryOpResult:
         old_text = old_text.strip()
         new_content = new_content.strip()
-        if not old_text:
-            return MemoryOpResult(False, "old_text cannot be empty.")
         if not new_content:
             return MemoryOpResult(False, "new_content cannot be empty. Use 'remove' to delete.")
         blocked = scan_memory_content(new_content)
@@ -259,21 +310,29 @@ async def replace(self, target: Target, old_text: str, new_content: str) -> Memo
                 return MemoryOpResult(
                     False, f"Memory read failed ({exc}); aborting write to avoid data loss."
                 )
-            idx = self._match_one(entries, old_text)
+            idx = self._locate(entries, old_text, index)
             if isinstance(idx, MemoryOpResult):
                 return idx
             limit = self._char_limit(target)
             candidate = list(entries)
             candidate[idx] = new_content
-            if len(ENTRY_DELIMITER.join(candidate)) > limit:
-                return MemoryOpResult(False, f"Replacement would exceed the {limit}-char limit.")
+            projected = self._used(candidate)
+            if projected > limit:
+                over = projected - limit
+                return MemoryOpResult(
+                    False,
+                    f"Replacement too large by {over} chars: result would be "
+                    f"{projected}/{limit}. Shorten the new text by ≥{over} chars, or remove "
+                    f"another entry first.\nCurrent entries:\n{self._inventory(entries)}",
+                    full=True,
+                )
             await self._write_entries(target, candidate)
         return MemoryOpResult(True, "Entry replaced.")
 
-    async def remove(self, target: Target, old_text: str) -> MemoryOpResult:
+    async def remove(
+        self, target: Target, old_text: str, *, index: int | None = None
+    ) -> MemoryOpResult:
         old_text = old_text.strip()
-        if not old_text:
-            return MemoryOpResult(False, "old_text cannot be empty.")
         path = await self._path_for(target)
         async with self._async_lock, self._file_lock(path):
             try:
@@ -282,13 +341,38 @@ async def remove(self, target: Target, old_text: str) -> MemoryOpResult:
                 return MemoryOpResult(
                     False, f"Memory read failed ({exc}); aborting write to avoid data loss."
                 )
-            idx = self._match_one(entries, old_text)
+            idx = self._locate(entries, old_text, index)
             if isinstance(idx, MemoryOpResult):
                 return idx
             entries.pop(idx)
             await self._write_entries(target, entries)
         return MemoryOpResult(True, "Entry removed.")
 
+    async def capacity(self, target: Target) -> tuple[int, int, int]:
+        """Return ``(used, limit, free)`` chars for ``target`` (free accounts for the
+        delimiter a new entry would cost). Used by the UI to show/explain capacity."""
+        entries = await self.read_entries(target)
+        limit = self._char_limit(target)
+        used = self._used(entries)
+        free = max(0, limit - used - self._append_overhead(entries))
+        return used, limit, free
+
+    async def status(self, target: Target) -> str:
+        """Read-only capacity + inventory snapshot for mid-session introspection.
+
+        Lets the agent see what is stored, at what size, and exactly how much room
+        is free before attempting a write — so it can remove/consolidate instead of
+        repeatedly retrying an over-budget add.
+        """
+        entries = await self.read_entries(target)
+        limit = self._char_limit(target)
+        used = self._used(entries)
+        free = max(0, limit - used - self._append_overhead(entries))
+        return (
+            f"{self._filename(target)}: {used}/{limit} chars across {len(entries)} "
+            f"entries; {free} free for a new entry.\nCurrent entries:\n{self._inventory(entries)}"
+        )
+
     async def append_journal(self, recap: str) -> MemoryOpResult:
         """Prepend one stable session recap to ``JOURNAL.md`` if it is new."""
         recap = recap.strip()