Merge remote-tracking branch 'origin/main' into codex/review-pr-3929

tests/agent/test_context_builder.py

@@ -139,6 +139,13 @@ class TestLoadBootstrapFiles:
         for name in ContextBuilder.BOOTSTRAP_FILES:
             assert f"## {name}" in result
 
+    def test_legacy_tools_md_is_not_bootstrapped(self, tmp_path):
+        (tmp_path / "TOOLS.md").write_text("workspace tool notes", encoding="utf-8")
+        builder = _builder(tmp_path)
+        result = builder._load_bootstrap_files()
+        assert "TOOLS.md" not in result
+        assert "workspace tool notes" not in result
+
     def test_utf8_content(self, tmp_path):
         (tmp_path / "AGENTS.md").write_text("用中文回复", encoding="utf-8")
         builder = _builder(tmp_path)
@@ -171,6 +178,37 @@ class TestIsTemplateContent:
         assert ContextBuilder._is_template_content("totally different", "memory/MEMORY.md") is False
 
 
+# ---------------------------------------------------------------------------
+# Bundled bootstrap templates
+# ---------------------------------------------------------------------------
+
+
+class TestBundledToolContract:
+    def test_tool_contract_balances_general_and_coding_workflows(self):
+        from importlib.resources import files as pkg_files
+
+        tpl = pkg_files("nanobot") / "templates" / "agent" / "tool_contract.md"
+        content = tpl.read_text(encoding="utf-8")
+
+        assert "## General Tool Contract" in content
+        assert "Use the narrowest structured tool" in content
+        assert "Do not use `exec` as a universal workaround" in content
+        assert "## File and Coding Workflows" in content
+        assert "apply_patch" in content
+        assert "## Web and External Information" in content
+        assert "## Messaging and Media" in content
+        assert "## Scheduling and Background Work" in content
+        assert "pure coding" not in content.lower()
+
+    def test_tool_contract_is_injected_without_workspace_file(self, tmp_path):
+        builder = _builder(tmp_path)
+        prompt = builder.build_system_prompt()
+
+        assert "# Tool Usage Notes" in prompt
+        assert "## General Tool Contract" in prompt
+        assert "Do not use `exec` as a universal workaround" in prompt
+
+
 # ---------------------------------------------------------------------------
 # _build_user_content
 # ---------------------------------------------------------------------------

tests/agent/test_onboard_logic.py

@@ -346,6 +346,26 @@ class TestSyncWorkspaceTemplates:
         content = (workspace / "AGENTS.md").read_text()
         assert content == "existing content"
 
+    def test_does_not_create_tools_md(self, tmp_path):
+        """Tool contract is injected internally, not copied into user workspaces."""
+        workspace = tmp_path / "workspace"
+
+        added = sync_workspace_templates(workspace, silent=True)
+
+        assert "TOOLS.md" not in added
+        assert not (workspace / "TOOLS.md").exists()
+
+    def test_preserves_existing_tools_md_without_overwriting(self, tmp_path):
+        """Legacy user workspaces may have TOOLS.md; sync should leave it untouched."""
+        workspace = tmp_path / "workspace"
+        workspace.mkdir(parents=True)
+        tools_path = workspace / "TOOLS.md"
+        tools_path.write_text("custom tool notes", encoding="utf-8")
+
+        sync_workspace_templates(workspace, silent=True)
+
+        assert tools_path.read_text(encoding="utf-8") == "custom tool notes"
+
     def test_creates_memory_directory(self, tmp_path):
         """Should create memory directory structure."""
         workspace = tmp_path / "workspace"

tests/channels/test_signal_markdown.py

@@ -0,0 +1,525 @@
+"""Unit tests for the Signal markdown → plain text + textStyle converter."""
+
+from nanobot.channels.signal import _markdown_to_signal, _partition_styles
+from nanobot.utils.helpers import split_message
+
+
+def _utf16_len(s: str) -> int:
+    return len(s.encode("utf-16-le")) // 2
+
+
+def styles_for(plain: str, text_styles: list[str]) -> dict[str, list[str]]:
+    """Return a dict mapping each styled substring to its style list."""
+    result: dict[str, list[str]] = {}
+    for entry in text_styles:
+        start_s, length_s, style = entry.split(":", 2)
+        start, length = int(start_s), int(length_s)
+        span = plain[start : start + length]
+        result.setdefault(span, []).append(style)
+    return result
+
+
+def utf16_styles_for(plain: str, text_styles: list[str]) -> dict[str, list[str]]:
+    """Like styles_for, but slices `plain` using UTF-16 offsets (Signal's units)."""
+    encoded = plain.encode("utf-16-le")
+    result: dict[str, list[str]] = {}
+    for entry in text_styles:
+        start_s, length_s, style = entry.split(":", 2)
+        start, length = int(start_s), int(length_s)
+        span = encoded[start * 2 : (start + length) * 2].decode("utf-16-le")
+        result.setdefault(span, []).append(style)
+    return result
+
+
+# ---------------------------------------------------------------------------
+# Basic cases
+# ---------------------------------------------------------------------------
+
+
+def test_empty():
+    plain, styles = _markdown_to_signal("")
+    assert plain == ""
+    assert styles == []
+
+
+def test_plain_text():
+    plain, styles = _markdown_to_signal("hello world")
+    assert plain == "hello world"
+    assert styles == []
+
+
+def test_bold_stars():
+    plain, styles = _markdown_to_signal("say **hello** now")
+    assert plain == "say hello now"
+    assert styles_for(plain, styles) == {"hello": ["BOLD"]}
+
+
+def test_bold_underscores():
+    plain, styles = _markdown_to_signal("say __hello__ now")
+    assert plain == "say hello now"
+    assert styles_for(plain, styles) == {"hello": ["BOLD"]}
+
+
+def test_italic_star():
+    plain, styles = _markdown_to_signal("say *hello* now")
+    assert plain == "say hello now"
+    assert styles_for(plain, styles) == {"hello": ["ITALIC"]}
+
+
+def test_italic_underscore():
+    plain, styles = _markdown_to_signal("say _hello_ now")
+    assert plain == "say hello now"
+    assert styles_for(plain, styles) == {"hello": ["ITALIC"]}
+
+
+def test_strikethrough():
+    plain, styles = _markdown_to_signal("say ~~hello~~ now")
+    assert plain == "say hello now"
+    assert styles_for(plain, styles) == {"hello": ["STRIKETHROUGH"]}
+
+
+# ---------------------------------------------------------------------------
+# Code
+# ---------------------------------------------------------------------------
+
+
+def test_inline_code():
+    plain, styles = _markdown_to_signal("run `ls -la` here")
+    assert plain == "run ls -la here"
+    assert styles_for(plain, styles) == {"ls -la": ["MONOSPACE"]}
+
+
+def test_code_block():
+    plain, styles = _markdown_to_signal("```\nprint('hi')\n```")
+    assert "print('hi')" in plain
+    assert styles_for(plain, styles).get("print('hi')\n") == ["MONOSPACE"] or "MONOSPACE" in str(
+        styles_for(plain, styles)
+    )
+
+
+def test_code_block_with_lang():
+    plain, styles = _markdown_to_signal("```python\ncode\n```")
+    assert "code" in plain
+    assert any("MONOSPACE" in s for s in styles)
+
+
+def test_code_block_not_processed_further():
+    """Markdown inside a code block must not be styled."""
+    plain, styles = _markdown_to_signal("```\n**not bold**\n```")
+    assert "**not bold**" in plain
+    # Only MONOSPACE should be applied, no BOLD
+    for entry in styles:
+        assert "BOLD" not in entry
+
+
+def test_inline_code_not_processed_further():
+    """Markdown inside inline code must not be styled."""
+    plain, styles = _markdown_to_signal("use `**raw**` please")
+    assert "**raw**" in plain
+    for entry in styles:
+        assert "BOLD" not in entry
+
+
+# ---------------------------------------------------------------------------
+# Headers
+# ---------------------------------------------------------------------------
+
+
+def test_header_becomes_bold():
+    plain, styles = _markdown_to_signal("# My Title")
+    assert plain == "My Title"
+    assert styles_for(plain, styles) == {"My Title": ["BOLD"]}
+
+
+def test_h2_becomes_bold():
+    plain, styles = _markdown_to_signal("## Sub-section")
+    assert plain == "Sub-section"
+    assert styles_for(plain, styles) == {"Sub-section": ["BOLD"]}
+
+
+# ---------------------------------------------------------------------------
+# Blockquotes
+# ---------------------------------------------------------------------------
+
+
+def test_blockquote_strips_marker():
+    plain, styles = _markdown_to_signal("> some quote")
+    assert plain == "some quote"
+    assert styles == []
+
+
+# ---------------------------------------------------------------------------
+# Lists
+# ---------------------------------------------------------------------------
+
+
+def test_bullet_dash():
+    plain, styles = _markdown_to_signal("- item one")
+    assert plain == "• item one"
+
+
+def test_bullet_star():
+    plain, styles = _markdown_to_signal("* item two")
+    assert plain == "• item two"
+
+
+def test_numbered_list():
+    plain, styles = _markdown_to_signal("1. first\n2. second")
+    assert "1. first" in plain
+    assert "2. second" in plain
+
+
+# ---------------------------------------------------------------------------
+# Links
+# ---------------------------------------------------------------------------
+
+
+def test_link_text_differs_from_url():
+    plain, styles = _markdown_to_signal("[Click here](https://example.com)")
+    assert plain == "Click here (https://example.com)"
+    assert styles == []
+
+
+def test_link_text_equals_url():
+    plain, styles = _markdown_to_signal("[https://example.com](https://example.com)")
+    assert plain == "https://example.com"
+    assert styles == []
+
+
+def test_link_text_equals_url_without_scheme():
+    plain, styles = _markdown_to_signal("[example.com](https://example.com)")
+    assert plain == "https://example.com"
+
+
+# ---------------------------------------------------------------------------
+# Mixed / nesting
+# ---------------------------------------------------------------------------
+
+
+def test_bold_and_italic_adjacent():
+    plain, styles = _markdown_to_signal("**bold** and *italic*")
+    assert plain == "bold and italic"
+    sd = styles_for(plain, styles)
+    assert sd.get("bold") == ["BOLD"]
+    assert sd.get("italic") == ["ITALIC"]
+
+
+def test_header_with_inline_code():
+    """Header becomes BOLD; code inside becomes MONOSPACE (not double-BOLD)."""
+    plain, styles = _markdown_to_signal("# Use `grep`")
+    assert plain == "Use grep"
+    sd = styles_for(plain, styles)
+    assert "BOLD" in sd.get("Use ", []) or "BOLD" in str(styles)
+    assert "MONOSPACE" in sd.get("grep", [])
+
+
+def test_multiline_mixed():
+    md = "**Title**\n\nSome *italic* text.\n\n- bullet\n- another"
+    plain, styles = _markdown_to_signal(md)
+    assert "Title" in plain
+    assert "italic" in plain
+    assert "• bullet" in plain
+    sd = styles_for(plain, styles)
+    assert "BOLD" in sd.get("Title", [])
+    assert "ITALIC" in sd.get("italic", [])
+
+
+# ---------------------------------------------------------------------------
+# Table rendering
+# ---------------------------------------------------------------------------
+
+
+def test_table_rendered_as_monospace():
+    md = "| A | B |\n| - | - |\n| 1 | 2 |"
+    plain, styles = _markdown_to_signal(md)
+    assert "A" in plain and "B" in plain
+    assert any("MONOSPACE" in s for s in styles)
+
+
+# ---------------------------------------------------------------------------
+# Style range format
+# ---------------------------------------------------------------------------
+
+
+def test_style_range_format():
+    """Each style entry must be 'start:length:STYLE'."""
+    _, styles = _markdown_to_signal("**bold** text")
+    for entry in styles:
+        parts = entry.split(":")
+        assert len(parts) == 3
+        assert parts[0].isdigit()
+        assert parts[1].isdigit()
+        assert parts[2] in {"BOLD", "ITALIC", "STRIKETHROUGH", "MONOSPACE", "SPOILER"}
+
+
+def test_style_ranges_are_within_bounds():
+    text = "hello **world** end"
+    plain, styles = _markdown_to_signal(text)
+    for entry in styles:
+        start_s, length_s, _ = entry.split(":", 2)
+        start, length = int(start_s), int(length_s)
+        assert start >= 0
+        assert start + length <= len(plain)
+
+
+# ---------------------------------------------------------------------------
+# Non-BMP / UTF-16 offsets
+#
+# Signal's BodyRange (and signal-cli's textStyle) interprets start/length in
+# UTF-16 code units. Python's len() counts code points, so characters outside
+# the BMP (emojis, supplementary CJK) shift offsets by +1 per occurrence.
+# ---------------------------------------------------------------------------
+
+
+def assert_within_utf16_bounds(plain: str, styles: list[str]) -> None:
+    limit = _utf16_len(plain)
+    for entry in styles:
+        start_s, length_s, _ = entry.split(":", 2)
+        start, length = int(start_s), int(length_s)
+        assert start >= 0
+        assert start + length <= limit, f"range {entry} exceeds utf-16 length {limit} of {plain!r}"
+
+
+def test_bold_with_emoji_inside():
+    plain, styles = _markdown_to_signal("**hi 🎉 bye**")
+    assert plain == "hi 🎉 bye"
+    assert utf16_styles_for(plain, styles) == {"hi 🎉 bye": ["BOLD"]}
+    assert_within_utf16_bounds(plain, styles)
+
+
+def test_italic_with_trailing_emoji():
+    plain, styles = _markdown_to_signal("*bye 🎉*")
+    assert plain == "bye 🎉"
+    assert utf16_styles_for(plain, styles) == {"bye 🎉": ["ITALIC"]}
+    assert_within_utf16_bounds(plain, styles)
+
+
+def test_bold_after_emoji_prefix():
+    plain, styles = _markdown_to_signal("🎉 **bold**")
+    assert plain == "🎉 bold"
+    assert utf16_styles_for(plain, styles) == {"bold": ["BOLD"]}
+    assert_within_utf16_bounds(plain, styles)
+
+
+def test_bold_after_and_inside_emoji():
+    plain, styles = _markdown_to_signal("🎉 **a 🎊 b**")
+    assert plain == "🎉 a 🎊 b"
+    assert utf16_styles_for(plain, styles) == {"a 🎊 b": ["BOLD"]}
+    assert_within_utf16_bounds(plain, styles)
+
+
+def test_supplementary_cjk_in_bold():
+    """Non-BMP CJK (U+20BB7) proves the bug is UTF-16, not emoji-specific."""
+    plain, styles = _markdown_to_signal("**𠮷野家**")
+    assert plain == "𠮷野家"
+    assert utf16_styles_for(plain, styles) == {"𠮷野家": ["BOLD"]}
+    assert_within_utf16_bounds(plain, styles)
+
+
+def test_zwj_emoji_in_bold():
+    """ZWJ family sequence = multiple surrogate pairs + BMP ZWJs."""
+    plain, styles = _markdown_to_signal("**hi 👨‍👩‍👧 bye**")
+    assert plain == "hi 👨‍👩‍👧 bye"
+    assert utf16_styles_for(plain, styles) == {"hi 👨‍👩‍👧 bye": ["BOLD"]}
+    assert_within_utf16_bounds(plain, styles)
+
+
+def test_ascii_offsets_unchanged():
+    """ASCII-only path must produce the same offsets as before the UTF-16 fix."""
+    plain, styles = _markdown_to_signal("**bold** plain *it*")
+    assert plain == "bold plain it"
+    assert sorted(styles) == sorted(["0:4:BOLD", "11:2:ITALIC"])
+
+
+def test_reported_daily_brief_pattern():
+    """Regression for the reported bug: a single non-BMP emoji shifts every
+    subsequent styled span left by 1 UTF-16 unit, lopping off the last letter.
+    """
+    md = (
+        "**Weather**\n"
+        "- Conditions: 🌩️ Thunderstorms\n\n"
+        "**News**\n"
+        "*World*\n"
+        "*Local*\n\n"
+        "**Quote of the Day**"
+    )
+    plain, styles = _markdown_to_signal(md)
+    sd = utf16_styles_for(plain, styles)
+    assert sd.get("Weather") == ["BOLD"]
+    assert sd.get("News") == ["BOLD"]
+    assert sd.get("World") == ["ITALIC"]
+    assert sd.get("Local") == ["ITALIC"]
+    assert sd.get("Quote of the Day") == ["BOLD"]
+    assert_within_utf16_bounds(plain, styles)
+
+
+# ---------------------------------------------------------------------------
+# Chunk redistribution
+#
+# split_message can break a long Signal payload into multiple chunks. The
+# style ranges from _markdown_to_signal are anchored to the full text, so
+# they must be redistributed per-chunk with rebased offsets — otherwise
+# styles for chunks 1..N are silently lost.
+# ---------------------------------------------------------------------------
+
+
+def _resolve_chunk_styles(text: str, max_len: int) -> tuple[list[str], list[list[str]]]:
+    """Helper: full markdown → signal pipeline, including chunking."""
+    plain, styles = _markdown_to_signal(text)
+    chunks = split_message(plain, max_len) if plain else [""]
+    return chunks, _partition_styles(plain, chunks, styles)
+
+
+def test_partition_styles_single_chunk_passthrough():
+    plain, styles = _markdown_to_signal("**bold** plain *it*")
+    parts = _partition_styles(plain, [plain], styles)
+    assert parts == [styles]
+
+
+def test_partition_styles_no_styles():
+    plain = "hello world"
+    assert _partition_styles(plain, [plain], []) == [[]]
+    assert _partition_styles(plain, ["hello", "world"], []) == [[], []]
+
+
+def test_partition_styles_drops_styles_outside_chunks():
+    """Whitespace trimmed by split_message must not carry a style range."""
+    plain = "a   b"
+    # Fake a style spanning the trimmed whitespace only.
+    chunks = ["a", "b"]
+    parts = _partition_styles(plain, chunks, ["1:3:BOLD"])
+    assert parts == [[], []]
+
+
+def test_partition_styles_long_message_preserves_chunk_one_styles():
+    """A bold span deep in the message must follow the message into chunk 1."""
+    # Two ~30-char paragraphs separated by a blank line, then **tail**.
+    line_a = "alpha " * 5  # 30 chars, ends with space
+    line_b = "beta " * 5
+    md = f"{line_a.strip()}\n\n{line_b.strip()}\n\n**tail**"
+    plain, styles = _markdown_to_signal(md)
+    # Force a split between the paragraphs.
+    max_len = len(line_a.strip()) + 2  # fits paragraph A + the "\n\n"
+    chunks = split_message(plain, max_len)
+    assert len(chunks) >= 2, "test setup must produce a split"
+    parts = _partition_styles(plain, chunks, styles)
+    # The bold "tail" should land in the last chunk, with chunk-relative offset.
+    final_chunk = chunks[-1]
+    final_styles = parts[-1]
+    assert any("BOLD" in s for s in final_styles)
+    for entry in final_styles:
+        s, ln, _ = entry.split(":", 2)
+        start, length = int(s), int(ln)
+        slice_ = final_chunk.encode("utf-16-le")[start * 2 : (start + length) * 2].decode(
+            "utf-16-le"
+        )
+        assert slice_ == "tail"
+
+
+def test_partition_styles_chunk_zero_styles_unchanged():
+    """Styles entirely in chunk 0 keep their original offsets."""
+    md = "**head** middle and **tail**"
+    plain, styles = _markdown_to_signal(md)
+    # Split so chunk 0 contains "head" and part of the rest, chunk 1 contains "tail".
+    chunks = split_message(plain, 12)
+    assert len(chunks) >= 2
+    parts = _partition_styles(plain, chunks, styles)
+    # "head" lives in chunk 0; assert its offset is unchanged (chunk 0 starts at 0).
+    head_entries = [s for s in parts[0] if "BOLD" in s]
+    assert any(s.startswith("0:4:") for s in head_entries)
+
+
+def test_partition_styles_with_non_bmp_chunk_offset():
+    """Chunk-start offsets must be expressed in UTF-16 code units."""
+    # Emoji in chunk 0, bold in chunk 1.
+    md = "🎉 alpha beta gamma\n\n**tail**"
+    plain, styles = _markdown_to_signal(md)
+    chunks = split_message(plain, 18)
+    assert len(chunks) >= 2
+    parts = _partition_styles(plain, chunks, styles)
+    final_styles = parts[-1]
+    assert any("BOLD" in s for s in final_styles)
+    final_chunk = chunks[-1]
+    for entry in final_styles:
+        s, ln, _ = entry.split(":", 2)
+        start, length = int(s), int(ln)
+        slice_ = final_chunk.encode("utf-16-le")[start * 2 : (start + length) * 2].decode(
+            "utf-16-le"
+        )
+        assert slice_ == "tail"
+
+
+def test_partition_styles_range_spanning_chunks_is_split():
+    """A style range that straddles a chunk boundary gets sliced into both chunks."""
+    # Construct manually: plain = "abc def", style covers "abc def" (whole thing).
+    plain = "abc def"
+    chunks = split_message(plain, 4)  # "abc" / "def"
+    assert chunks == ["abc", "def"]
+    parts = _partition_styles(plain, chunks, ["0:7:BOLD"])
+    # Chunk 0 holds 0:3:BOLD, chunk 1 holds 0:3:BOLD (length=3 each, "def" only
+    # since the space was trimmed by lstrip).
+    assert parts[0] == ["0:3:BOLD"]
+    assert parts[1] == ["0:3:BOLD"]
+
+
+# ---------------------------------------------------------------------------
+# Adjacency, nesting, and malformed input
+# ---------------------------------------------------------------------------
+
+
+def test_bold_italic_combo_outer_bold_inner_italic():
+    """`**_combo_**` carries both BOLD and ITALIC over the same span."""
+    plain, styles = _markdown_to_signal("**_combo_**")
+    assert plain == "combo"
+    sd = styles_for(plain, styles)
+    assert set(sd.get("combo", [])) == {"BOLD", "ITALIC"}
+
+
+def test_bold_and_italic_adjacent_no_separator():
+    """`**bold***italic*` produces BOLD on `bold` and ITALIC on `italic`."""
+    plain, styles = _markdown_to_signal("**bold***italic*")
+    assert plain == "bolditalic"
+    sd = styles_for(plain, styles)
+    assert sd.get("bold") == ["BOLD"]
+    assert sd.get("italic") == ["ITALIC"]
+
+
+def test_unclosed_bold_falls_through_as_plain():
+    """An unmatched `**` opener round-trips as literal text with no style."""
+    plain, styles = _markdown_to_signal("**bold")
+    assert plain == "**bold"
+    assert styles == []
+
+
+def test_unclosed_inline_code_falls_through_as_plain():
+    """An unmatched backtick round-trips as literal text with no style."""
+    plain, styles = _markdown_to_signal("use `grep")
+    assert plain == "use `grep"
+    assert styles == []
+
+
+def test_inline_code_inside_blockquote():
+    """Blockquote prefix is stripped; inline code becomes MONOSPACE."""
+    plain, styles = _markdown_to_signal("> use `grep`")
+    assert plain == "use grep"
+    sd = styles_for(plain, styles)
+    assert sd.get("grep") == ["MONOSPACE"]
+
+
+def test_header_with_inner_bold_produces_contiguous_bold_ranges():
+    """`# **wrap** me` — header forces BOLD over the whole line; the inner `**`
+    splits the run, yielding two contiguous BOLD ranges that together cover
+    "wrap me". This is intentional — Signal renders adjacent same-style ranges
+    as a single visual span.
+    """
+    plain, styles = _markdown_to_signal("# **wrap** me")
+    assert plain == "wrap me"
+    # Both ranges are BOLD; collectively they cover the whole "wrap me".
+    bold_ranges = [s for s in styles if s.endswith(":BOLD")]
+    assert len(bold_ranges) == 2
+    covered = set()
+    for entry in bold_ranges:
+        start, length, _ = entry.split(":", 2)
+        for i in range(int(start), int(start) + int(length)):
+            covered.add(i)
+    assert covered == set(range(len(plain)))

tests/channels/test_websocket_channel.py

@@ -1055,6 +1055,7 @@ async def test_settings_api_returns_safe_subset_and_updates_whitelist(
         }
         assert image_providers["openrouter"]["label"] == "OpenRouter"
         assert image_providers["openrouter"]["configured"] is False
+        assert image_providers["openai_codex"]["configured"] is True
         assert image_providers["gemini"]["label"] == "Gemini"
         assert body["runtime"]["config_path"] == str(config_path)
         workspace_path = body["runtime"]["workspace_path"].replace("\\", "/")

tests/channels/test_weixin_channel.py

@@ -1,6 +1,7 @@
 import asyncio
 import json
 import tempfile
+import time
 from pathlib import Path
 from types import SimpleNamespace
 from unittest.mock import AsyncMock
@@ -374,6 +375,7 @@ async def test_send_uses_typing_start_and_cancel_when_ticket_available() -> None
     channel._client = object()
     channel._token = "token"
     channel._context_tokens["wx-user"] = "ctx-typing"
+    channel._context_token_at["wx-user"] = time.time()
     channel._send_text = AsyncMock()
     channel._api_post = AsyncMock(
         side_effect=[
@@ -402,6 +404,7 @@ async def test_send_still_sends_text_when_typing_ticket_missing() -> None:
     channel._client = object()
     channel._token = "token"
     channel._context_tokens["wx-user"] = "ctx-no-ticket"
+    channel._context_token_at["wx-user"] = time.time()
     channel._send_text = AsyncMock()
     channel._api_post = AsyncMock(return_value={"ret": 1, "errmsg": "no config"})
 
@@ -1254,3 +1257,526 @@ async def test_send_text_succeeds_on_zero_errcode() -> None:
     await channel._send_text("wx-user", "hello", "ctx-ok")
 
     channel._api_post.assert_awaited_once()
+
+
+@pytest.mark.asyncio
+async def test_send_text_raises_on_nonzero_ret_even_when_errcode_zero() -> None:
+    """_send_text must raise when the API returns ret != 0, even if errcode is 0.
+
+    The iLink API signals failure through either field.  Checking only errcode
+    caused silent message drops (responses generated but never delivered).
+    """
+    channel, _bus = _make_channel()
+    channel._client = object()
+    channel._token = "token"
+    channel._api_post = AsyncMock(
+        return_value={"ret": -100, "errcode": 0, "errmsg": "internal error"}
+    )
+
+    with pytest.raises(RuntimeError, match="WeChat send text error.*ret=-100.*errcode=0"):
+        await channel._send_text("wx-user", "hello", "ctx-ok")
+
+    channel._api_post.assert_awaited_once()
+
+
+# ---------------------------------------------------------------------------
+# Tests for _poll_once not silently dropping messages on processing errors
+# ---------------------------------------------------------------------------
+
+
+@pytest.mark.asyncio
+async def test_poll_once_logs_exception_on_process_message_failure(monkeypatch) -> None:
+    """When _process_message raises, _poll_once must log the error and continue
+    processing remaining messages instead of silently swallowing the exception."""
+    channel, _bus = _make_channel()
+    channel._client = SimpleNamespace(timeout=None)
+    channel._token = "token"
+    channel._get_updates_buf = "old-buf"
+
+    calls = []
+    logged_messages: list[str] = []
+
+    async def _failing_process(msg: dict) -> None:
+        calls.append(msg.get("message_id"))
+        if msg.get("message_id") == "msg-1":
+            raise RuntimeError("processing failed")
+
+    channel._process_message = _failing_process  # type: ignore[method-assign]
+
+    monkeypatch.setattr(
+        channel.logger,
+        "exception",
+        lambda message, *args, **kwargs: logged_messages.append(str(message)),
+    )
+
+    channel._api_post = AsyncMock(  # type: ignore[method-assign]
+        return_value={
+            "ret": 0,
+            "errcode": 0,
+            "get_updates_buf": "new-buf",
+            "msgs": [
+                {"message_id": "msg-1", "message_type": 1},
+                {"message_id": "msg-2", "message_type": 1},
+            ],
+        }
+    )
+
+    await channel._poll_once()
+
+    # Both messages should have been attempted
+    assert calls == ["msg-1", "msg-2"]
+    # Buffer should still advance (already updated before processing)
+    assert channel._get_updates_buf == "new-buf"
+    # Error should be logged
+    assert any("Failed to process WeChat message" in m for m in logged_messages)
+
+
+@pytest.mark.asyncio
+async def test_poll_loop_logs_exception_and_continues_on_poll_failure(monkeypatch) -> None:
+    """When _poll_once raises a non-timeout exception, the start() loop must log
+    the error and continue polling instead of exiting silently."""
+    channel, _bus = _make_channel()
+    channel._client = object()
+    channel._token = "token"
+    channel.config.token = "token"  # skip QR login in start()
+    channel._running = True
+
+    call_count = 0
+    logged_messages: list[str] = []
+
+    async def _failing_poll() -> None:
+        nonlocal call_count
+        call_count += 1
+        if call_count == 1:
+            raise RuntimeError("poll exploded")
+        channel._running = False  # Stop after second call
+
+    channel._poll_once = _failing_poll  # type: ignore[method-assign]
+
+    monkeypatch.setattr(
+        channel.logger,
+        "exception",
+        lambda message, *args, **kwargs: logged_messages.append(str(message)),
+    )
+
+    # Use a tiny retry delay so the test finishes quickly
+    original_retry = weixin_mod.RETRY_DELAY_S
+    weixin_mod.RETRY_DELAY_S = 0.01
+    try:
+        await channel.start()
+    finally:
+        weixin_mod.RETRY_DELAY_S = original_retry
+
+    assert call_count == 2
+    assert any("WeChat poll loop error" in m for m in logged_messages)
+
+
+# ---------------------------------------------------------------------------
+# Tool-hint buffering
+# ---------------------------------------------------------------------------
+
+
+@pytest.mark.asyncio
+async def test_buffer_single_tool_hint_not_sent_immediately() -> None:
+    channel, _bus = _make_channel()
+    channel._client = object()
+    channel._token = "token"
+    channel.send_tool_hints = True
+    channel._context_tokens["wx-user"] = "ctx-1"
+    channel._context_token_at["wx-user"] = time.time()
+    channel._send_text = AsyncMock()
+
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "Using tool",
+                "media": [],
+                "metadata": {"_progress": True, "_tool_hint": True},
+            },
+        )()
+    )
+
+    channel._send_text.assert_not_awaited()
+    assert channel._pending_tool_hints["wx-user"] == ["Using tool"]
+
+
+@pytest.mark.asyncio
+async def test_buffer_multiple_tool_hints_flushed_on_final_answer() -> None:
+    channel, _bus = _make_channel()
+    channel._client = object()
+    channel._token = "token"
+    channel.send_tool_hints = True
+    channel._context_tokens["wx-user"] = "ctx-1"
+    channel._context_token_at["wx-user"] = time.time()
+    channel._send_text = AsyncMock()
+
+    for hint in ["tool1", "tool2"]:
+        await channel.send(
+            type(
+                "Msg",
+                (),
+                {
+                    "chat_id": "wx-user",
+                    "content": hint,
+                    "media": [],
+                    "metadata": {"_progress": True, "_tool_hint": True},
+                },
+            )()
+        )
+
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "Done",
+                "media": [],
+                "metadata": {},
+            },
+        )()
+    )
+
+    assert channel._send_text.await_count == 2
+    channel._send_text.assert_any_await("wx-user", "tool1\n\ntool2", "ctx-1")
+    channel._send_text.assert_any_await("wx-user", "Done", "ctx-1")
+    assert "wx-user" not in channel._pending_tool_hints
+
+
+@pytest.mark.asyncio
+async def test_thought_progress_flushes_tool_hints() -> None:
+    """Thoughts are visible progress messages and must act as separators,
+    flushing buffered tool hints before they are sent."""
+    channel, _bus = _make_channel()
+    channel._client = object()
+    channel._token = "token"
+    channel.send_tool_hints = True
+    channel._context_tokens["wx-user"] = "ctx-1"
+    channel._context_token_at["wx-user"] = time.time()
+    channel._send_text = AsyncMock()
+
+    # Buffer a tool hint
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "search 'foo'",
+                "media": [],
+                "metadata": {"_progress": True, "_tool_hint": True},
+            },
+        )()
+    )
+
+    # Send a thought — progress but not a tool_hint.
+    # It must act as a separator and flush the buffered hint.
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "Let me think...",
+                "media": [],
+                "metadata": {"_progress": True},
+            },
+        )()
+    )
+
+    # The buffered hint was flushed before the thought was sent.
+    channel._send_text.assert_any_await("wx-user", "search 'foo'", "ctx-1")
+    channel._send_text.assert_any_await("wx-user", "Let me think...", "ctx-1")
+    assert "wx-user" not in channel._pending_tool_hints
+
+    # Final answer arrives with nothing left to flush.
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "Done",
+                "media": [],
+                "metadata": {},
+            },
+        )()
+    )
+
+    assert channel._send_text.await_count == 3
+    channel._send_text.assert_any_await("wx-user", "Done", "ctx-1")
+
+
+@pytest.mark.asyncio
+async def test_reasoning_delta_does_not_flush_tool_hints() -> None:
+    """Reasoning deltas are invisible in WeChat and must NOT flush buffered
+    tool hints — otherwise hints separated only by hidden reasoning would
+    fail to coalesce."""
+    channel, _bus = _make_channel()
+    channel._client = object()
+    channel._token = "token"
+    channel.send_tool_hints = True
+    channel._context_tokens["wx-user"] = "ctx-1"
+    channel._context_token_at["wx-user"] = time.time()
+    channel._send_text = AsyncMock()
+
+    # Buffer a tool hint
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "search 'foo'",
+                "media": [],
+                "metadata": {"_progress": True, "_tool_hint": True},
+            },
+        )()
+    )
+
+    # Send a reasoning delta — invisible in WeChat, must NOT flush
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "Thinking step 1...",
+                "media": [],
+                "metadata": {"_progress": True, "_reasoning_delta": True},
+            },
+        )()
+    )
+
+    # Reasoning is invisible; hint stays buffered, _send_text not called
+    channel._send_text.assert_not_awaited()
+    assert channel._pending_tool_hints["wx-user"] == ["search 'foo'"]
+
+    # Final answer flushes the buffered hint
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "Done",
+                "media": [],
+                "metadata": {},
+            },
+        )()
+    )
+
+    channel._send_text.assert_any_await("wx-user", "search 'foo'", "ctx-1")
+    channel._send_text.assert_any_await("wx-user", "Done", "ctx-1")
+    assert "wx-user" not in channel._pending_tool_hints
+
+
+@pytest.mark.asyncio
+async def test_empty_progress_message_does_not_flush_tool_hints() -> None:
+    """Empty progress messages (e.g. after_iteration tool_events) have no
+    visible content and must NOT act as separators."""
+    channel, _bus = _make_channel()
+    channel._client = object()
+    channel._token = "token"
+    channel.send_tool_hints = True
+    channel._context_tokens["wx-user"] = "ctx-1"
+    channel._context_token_at["wx-user"] = time.time()
+    channel._send_text = AsyncMock()
+
+    # Buffer a tool hint
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "search 'foo'",
+                "media": [],
+                "metadata": {"_progress": True, "_tool_hint": True},
+            },
+        )()
+    )
+
+    # Send an empty progress message (no content, no media)
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "",
+                "media": [],
+                "metadata": {"_progress": True, "_tool_events": [{"phase": "end"}]},
+            },
+        )()
+    )
+
+    # Nothing should have been sent yet
+    channel._send_text.assert_not_awaited()
+    assert channel._pending_tool_hints["wx-user"] == ["search 'foo'"]
+
+    # Final answer flushes the buffered hint
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "Done",
+                "media": [],
+                "metadata": {},
+            },
+        )()
+    )
+
+    channel._send_text.assert_any_await("wx-user", "search 'foo'", "ctx-1")
+    channel._send_text.assert_any_await("wx-user", "Done", "ctx-1")
+    assert "wx-user" not in channel._pending_tool_hints
+
+
+@pytest.mark.asyncio
+async def test_buffer_flush_refreshes_context_token() -> None:
+    channel, _bus = _make_channel()
+    channel._client = object()
+    channel._token = "token"
+    channel.send_tool_hints = True
+    channel._context_tokens["wx-user"] = "ctx-old"
+    channel._context_token_at["wx-user"] = time.time()
+    channel._refresh_context_token_if_stale = AsyncMock(return_value="ctx-refreshed")
+    channel._send_text = AsyncMock()
+
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "hint",
+                "media": [],
+                "metadata": {"_progress": True, "_tool_hint": True},
+            },
+        )()
+    )
+
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "Done",
+                "media": [],
+                "metadata": {},
+            },
+        )()
+    )
+
+    assert channel._refresh_context_token_if_stale.await_count == 2
+    channel._refresh_context_token_if_stale.assert_any_await("wx-user", "ctx-old")
+    channel._send_text.assert_any_await("wx-user", "hint", "ctx-refreshed")
+
+
+@pytest.mark.asyncio
+async def test_buffer_flush_failure_does_not_block_final_answer() -> None:
+    channel, _bus = _make_channel()
+    channel._client = object()
+    channel._token = "token"
+    channel.send_tool_hints = True
+    channel._context_tokens["wx-user"] = "ctx-1"
+    channel._context_token_at["wx-user"] = time.time()
+    channel._send_text = AsyncMock(side_effect=[RuntimeError("boom"), None])
+
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "hint",
+                "media": [],
+                "metadata": {"_progress": True, "_tool_hint": True},
+            },
+        )()
+    )
+
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "Done",
+                "media": [],
+                "metadata": {},
+            },
+        )()
+    )
+
+    assert channel._send_text.await_count == 2
+    channel._send_text.assert_any_await("wx-user", "hint", "ctx-1")
+    channel._send_text.assert_any_await("wx-user", "Done", "ctx-1")
+
+
+@pytest.mark.asyncio
+async def test_buffer_flushed_on_stream_end() -> None:
+    channel, _bus = _make_channel()
+    channel._client = object()
+    channel._token = "token"
+    channel.send_tool_hints = True
+    channel._context_tokens["wx-user"] = "ctx-1"
+    channel._context_token_at["wx-user"] = time.time()
+    channel._send_text = AsyncMock()
+
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "hint",
+                "media": [],
+                "metadata": {"_progress": True, "_tool_hint": True},
+            },
+        )()
+    )
+
+    await channel.send_delta("wx-user", "", {"_stream_end": True})
+
+    channel._send_text.assert_awaited_once_with("wx-user", "hint", "ctx-1")
+    assert "wx-user" not in channel._pending_tool_hints
+
+
+@pytest.mark.asyncio
+async def test_stop_clears_buffer() -> None:
+    channel, _bus = _make_channel()
+    channel._pending_tool_hints["wx-user"] = ["hint1", "hint2"]
+    await channel.stop()
+    assert "wx-user" not in channel._pending_tool_hints
+
+
+@pytest.mark.asyncio
+async def test_send_tool_hints_false_drops_tool_hints() -> None:
+    channel, _bus = _make_channel()
+    channel._client = object()
+    channel._token = "token"
+    channel.send_tool_hints = False
+    channel._send_text = AsyncMock()
+
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "hint",
+                "media": [],
+                "metadata": {"_progress": True, "_tool_hint": True},
+            },
+        )()
+    )
+
+    channel._send_text.assert_not_awaited()
+    assert "wx-user" not in channel._pending_tool_hints

tests/config/test_model_presets.py

@@ -192,3 +192,20 @@ def test_match_provider_uses_preset_provider_when_forced() -> None:
     })
     name = config.get_provider_name()
     assert name == "anthropic"
+
+
+def test_match_provider_routes_forced_novita_model_api_models() -> None:
+    config = Config.model_validate({
+        "providers": {
+            "novita": {"apiKey": "sk-test"},
+        },
+        "agents": {
+            "defaults": {
+                "model": "deepseek-v4-pro",
+                "provider": "novita",
+            }
+        },
+    })
+
+    assert config.get_provider_name() == "novita"
+    assert config.get_api_base() == "https://api.novita.ai/openai"

tests/providers/test_custom_provider.py

@@ -56,6 +56,35 @@ def test_custom_provider_parse_chunks_accepts_plain_text_chunks() -> None:
     assert result.content == "hello world"
 
 
+def test_custom_provider_parse_chunks_deduplicates_parallel_tool_call_ids() -> None:
+    chunks = [{
+        "choices": [{
+            "finish_reason": "tool_calls",
+            "delta": {
+                "tool_calls": [
+                    {
+                        "index": 0,
+                        "id": "call_dup",
+                        "function": {"name": "read_file", "arguments": '{"path":"a.txt"}'},
+                    },
+                    {
+                        "index": 1,
+                        "id": "call_dup",
+                        "function": {"name": "read_file", "arguments": '{"path":"b.txt"}'},
+                    },
+                ],
+            },
+        }],
+    }]
+
+    result = OpenAICompatProvider._parse_chunks(chunks)
+    ids = [tool_call.id for tool_call in result.tool_calls or []]
+
+    assert ids[0] == "call_dup"
+    assert len(ids) == 2
+    assert len(set(ids)) == 2
+
+
 def test_local_provider_502_error_includes_reachability_hint() -> None:
     spec = find_by_name("ollama")
     with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):

tests/providers/test_image_generation.py

@@ -9,10 +9,13 @@ import pytest
 
 from nanobot.providers.image_generation import (
     AIHubMixImageGenerationClient,
+    CodexImageGenerationClient,
     GeminiImageGenerationClient,
     GeneratedImageResponse,
     ImageGenerationError,
     MiniMaxImageGenerationClient,
+    OllamaImageGenerationClient,
+    OpenAIImageGenerationClient,
     OpenRouterImageGenerationClient,
     StepFunImageGenerationClient,
 )
@@ -36,12 +39,14 @@ class FakeResponse:
         payload: dict[str, Any],
         status_code: int = 200,
         content: bytes = b"",
+        sse_lines: list[str] | None = None,
     ) -> None:
         self._payload = payload
         self.status_code = status_code
         self.text = str(payload)
         self.content = content
         self.request = httpx.Request("POST", "https://openrouter.ai/api/v1/chat/completions")
+        self._sse_lines = sse_lines
 
     def json(self) -> dict[str, Any]:
         return self._payload
@@ -51,6 +56,15 @@ class FakeResponse:
             response = httpx.Response(self.status_code, request=self.request, text=self.text)
             raise httpx.HTTPStatusError("failed", request=self.request, response=response)
 
+    async def aiter_lines(self):
+        if self._sse_lines is not None:
+            for line in self._sse_lines:
+                yield line
+            return
+        # Fallback: treat response text as SSE lines
+        for line in self.text.split("\n"):
+            yield line
+
 
 class FakeClient:
     def __init__(self, response: FakeResponse) -> None:
@@ -133,6 +147,54 @@ async def test_openrouter_image_generation_requires_api_key() -> None:
         await client.generate(prompt="draw", model="model")
 
 
+@pytest.mark.asyncio
+async def test_ollama_image_generation_payload_and_response() -> None:
+    raw_b64 = PNG_DATA_URL.removeprefix("data:image/png;base64,")
+    fake = FakeClient(FakeResponse({"image": raw_b64}))
+    client = OllamaImageGenerationClient(
+        api_key="ollama-test",
+        api_base="http://localhost:11434/v1/",
+        extra_headers={"X-Test": "1"},
+        extra_body={"seed": 123},
+        client=fake,  # type: ignore[arg-type]
+    )
+
+    response = await client.generate(
+        prompt="a sunset",
+        model="x/z-image-turbo",
+        aspect_ratio="16:9",
+        image_size="1K",
+    )
+
+    assert response.images == [PNG_DATA_URL]
+    assert response.content == ""
+
+    call = fake.calls[0]
+    assert call["url"] == "http://localhost:11434/api/generate"
+    assert call["headers"]["Authorization"] == "Bearer ollama-test"
+    assert call["headers"]["X-Test"] == "1"
+    body = call["json"]
+    assert body["model"] == "x/z-image-turbo"
+    assert body["prompt"] == "a sunset"
+    assert body["width"] == 1024
+    assert body["height"] == 576
+    assert body["steps"] == 0
+    assert body["stream"] is False
+    assert body["seed"] == 123
+
+
+@pytest.mark.asyncio
+async def test_ollama_image_generation_rejects_reference_images() -> None:
+    client = OllamaImageGenerationClient(api_key=None)
+
+    with pytest.raises(ImageGenerationError, match="reference images"):
+        await client.generate(
+            prompt="edit this",
+            model="x/z-image-turbo",
+            reference_images=["ref.png"],
+        )
+
+
 @pytest.mark.asyncio
 async def test_aihubmix_image_generation_payload_and_response() -> None:
     raw_b64 = PNG_DATA_URL.removeprefix("data:image/png;base64,")
@@ -531,3 +593,437 @@ async def test_stepfun_no_images_raises() -> None:
 
     with pytest.raises(ImageGenerationError, match="returned no images"):
         await client.generate(prompt="draw", model="step-image-edit-2")
+
+
+# ---------------------------------------------------------------------------
+# OpenAI
+# ---------------------------------------------------------------------------
+
+
+@pytest.mark.asyncio
+async def test_openai_payload_and_response() -> None:
+    fake = FakeClient(FakeResponse({"data": [{"b64_json": RAW_B64}]}))
+    client = OpenAIImageGenerationClient(
+        api_key="sk-openai-test",
+        api_base="https://api.openai.com/v1",
+        extra_headers={"X-Test": "1"},
+        client=fake,  # type: ignore[arg-type]
+    )
+
+    response = await client.generate(
+        prompt="a cat on the moon",
+        model="dall-e-3",
+        aspect_ratio="16:9",
+    )
+
+    assert response.images == [PNG_DATA_URL]
+    call = fake.calls[0]
+    assert call["url"] == "https://api.openai.com/v1/images/generations"
+    assert call["headers"]["Authorization"] == "Bearer sk-openai-test"
+    assert call["headers"]["X-Test"] == "1"
+    body = call["json"]
+    assert body["model"] == "dall-e-3"
+    assert body["prompt"] == "a cat on the moon"
+    assert body["response_format"] == "b64_json"
+    assert body["n"] == 1
+    assert body["size"] == "1792x1024"
+
+
+@pytest.mark.asyncio
+async def test_openai_b64_json_response_uses_detected_mime() -> None:
+    raw_b64 = base64.b64encode(JPEG_BYTES).decode("ascii")
+    fake = FakeClient(FakeResponse({"data": [{"b64_json": raw_b64}]}))
+    client = OpenAIImageGenerationClient(
+        api_key="sk-openai-test",
+        client=fake,  # type: ignore[arg-type]
+    )
+
+    response = await client.generate(prompt="draw", model="dall-e-3")
+
+    assert response.images == [f"data:image/jpeg;base64,{raw_b64}"]
+
+
+@pytest.mark.asyncio
+async def test_openai_url_download_fallback() -> None:
+    fake = FakeClient(FakeResponse({"data": [{"url": "https://cdn.example/image.png"}]}))
+    fake.get_response = FakeResponse({}, content=PNG_BYTES)
+    client = OpenAIImageGenerationClient(
+        api_key="sk-openai-test",
+        client=fake,  # type: ignore[arg-type]
+    )
+
+    response = await client.generate(prompt="draw", model="dall-e-3")
+
+    assert response.images[0].startswith("data:image/png;base64,")
+    assert fake.get_calls[0]["url"] == "https://cdn.example/image.png"
+
+
+@pytest.mark.asyncio
+async def test_openai_multiple_images() -> None:
+    fake = FakeClient(FakeResponse({
+        "data": [
+            {"b64_json": RAW_B64},
+            {"b64_json": RAW_B64},
+        ]
+    }))
+    client = OpenAIImageGenerationClient(
+        api_key="sk-openai-test",
+        client=fake,  # type: ignore[arg-type]
+    )
+
+    response = await client.generate(prompt="draw", model="dall-e-3")
+
+    assert len(response.images) == 2
+    assert response.images == [PNG_DATA_URL, PNG_DATA_URL]
+
+
+@pytest.mark.asyncio
+async def test_openai_aspect_ratio_to_size() -> None:
+    fake = FakeClient(FakeResponse({"data": [{"b64_json": RAW_B64}]}))
+    client = OpenAIImageGenerationClient(
+        api_key="sk-openai-test",
+        client=fake,  # type: ignore[arg-type]
+    )
+
+    await client.generate(prompt="draw", model="dall-e-3", aspect_ratio="1:1")
+    assert fake.calls[0]["json"]["size"] == "1024x1024"
+
+
+@pytest.mark.asyncio
+async def test_openai_dalle3_uses_supported_orientation_sizes() -> None:
+    fake = FakeClient(FakeResponse({"data": [{"b64_json": RAW_B64}]}))
+    client = OpenAIImageGenerationClient(
+        api_key="sk-openai-test",
+        client=fake,  # type: ignore[arg-type]
+    )
+
+    await client.generate(prompt="draw", model="dall-e-3", aspect_ratio="3:4")
+    await client.generate(prompt="draw", model="dall-e-3", aspect_ratio="4:3")
+
+    assert fake.calls[0]["json"]["size"] == "1024x1792"
+    assert fake.calls[1]["json"]["size"] == "1792x1024"
+
+
+@pytest.mark.asyncio
+async def test_openai_dalle2_uses_square_size_for_non_square_ratios() -> None:
+    fake = FakeClient(FakeResponse({"data": [{"b64_json": RAW_B64}]}))
+    client = OpenAIImageGenerationClient(
+        api_key="sk-openai-test",
+        client=fake,  # type: ignore[arg-type]
+    )
+
+    await client.generate(prompt="draw", model="dall-e-2", aspect_ratio="16:9")
+
+    assert fake.calls[0]["json"]["size"] == "1024x1024"
+
+
+@pytest.mark.asyncio
+async def test_openai_gpt_image_uses_supported_landscape_size() -> None:
+    fake = FakeClient(FakeResponse({"data": [{"b64_json": RAW_B64}]}))
+    client = OpenAIImageGenerationClient(
+        api_key="sk-openai-test",
+        client=fake,  # type: ignore[arg-type]
+    )
+
+    await client.generate(prompt="draw", model="gpt-image-1", aspect_ratio="16:9")
+
+    assert fake.calls[0]["json"]["size"] == "1536x1024"
+
+
+@pytest.mark.asyncio
+async def test_openai_gpt_image_uses_supported_orientation_sizes() -> None:
+    fake = FakeClient(FakeResponse({"data": [{"b64_json": RAW_B64}]}))
+    client = OpenAIImageGenerationClient(
+        api_key="sk-openai-test",
+        client=fake,  # type: ignore[arg-type]
+    )
+
+    await client.generate(prompt="draw", model="gpt-image-1", aspect_ratio="3:4")
+    await client.generate(prompt="draw", model="gpt-image-1", aspect_ratio="4:3")
+
+    assert fake.calls[0]["json"]["size"] == "1024x1536"
+    assert fake.calls[1]["json"]["size"] == "1536x1024"
+
+
+@pytest.mark.asyncio
+async def test_openai_default_size_when_no_aspect_ratio() -> None:
+    fake = FakeClient(FakeResponse({"data": [{"b64_json": RAW_B64}]}))
+    client = OpenAIImageGenerationClient(
+        api_key="sk-openai-test",
+        client=fake,  # type: ignore[arg-type]
+    )
+
+    await client.generate(prompt="draw", model="dall-e-3")
+
+    body = fake.calls[0]["json"]
+    assert body["size"] == "1024x1024"
+
+
+@pytest.mark.asyncio
+async def test_openai_ignores_explicit_size_unsupported_by_model_family() -> None:
+    fake = FakeClient(FakeResponse({"data": [{"b64_json": RAW_B64}]}))
+    client = OpenAIImageGenerationClient(
+        api_key="sk-openai-test",
+        client=fake,  # type: ignore[arg-type]
+    )
+
+    await client.generate(
+        prompt="draw",
+        model="dall-e-3",
+        aspect_ratio="16:9",
+        image_size="1536x1024",
+    )
+
+    body = fake.calls[0]["json"]
+    assert body["size"] == "1792x1024"
+
+
+@pytest.mark.asyncio
+async def test_openai_uses_explicit_image_size() -> None:
+    fake = FakeClient(FakeResponse({"data": [{"b64_json": RAW_B64}]}))
+    client = OpenAIImageGenerationClient(
+        api_key="sk-openai-test",
+        client=fake,  # type: ignore[arg-type]
+    )
+
+    await client.generate(
+        prompt="draw",
+        model="dall-e-3",
+        aspect_ratio="16:9",
+        image_size="1024x1024",
+    )
+
+    body = fake.calls[0]["json"]
+    assert body["size"] == "1024x1024"
+
+
+@pytest.mark.asyncio
+async def test_openai_requires_api_key() -> None:
+    client = OpenAIImageGenerationClient(api_key=None)
+
+    with pytest.raises(ImageGenerationError, match="API key"):
+        await client.generate(prompt="draw", model="dall-e-3")
+
+
+# ---------------------------------------------------------------------------
+# OpenAI Codex (Responses API)
+# ---------------------------------------------------------------------------
+
+
+@pytest.mark.asyncio
+async def test_codex_payload_and_response(monkeypatch) -> None:
+    import sys
+    from dataclasses import dataclass
+    from types import SimpleNamespace
+
+    @dataclass
+    class FakeToken:
+        account_id: str = "acct-123"
+        access: str = "oauth-token"
+
+    async def fake_to_thread(fn, *args, **kwargs):
+        return fn(*args, **kwargs)
+
+    monkeypatch.setattr("asyncio.to_thread", fake_to_thread)
+    fake_oauth = SimpleNamespace(get_token=lambda: FakeToken())
+    monkeypatch.setitem(sys.modules, "oauth_cli_kit", fake_oauth)
+
+    sse_lines = [
+        'data: {"type":"response.output_item.added","item":{"id":"ig_1","type":"image_generation_call","status":"in_progress"}}',
+        "",
+        f'data: {{"type":"response.output_item.done","item":{{"id":"ig_1","type":"image_generation_call","result":"{PNG_DATA_URL}","status":"completed"}}}}',
+        "",
+        'data: [DONE]',
+        "",
+    ]
+    fake = FakeClient(FakeResponse({}, sse_lines=sse_lines))
+    client = CodexImageGenerationClient(
+        api_key=None,
+        api_base="https://chatgpt.com/backend-api",
+        extra_headers={"X-Test": "1"},
+        client=fake,  # type: ignore[arg-type]
+    )
+
+    response = await client.generate(
+        prompt="draw a cat",
+        model="gpt-5.4",
+    )
+
+    assert response.images == [PNG_DATA_URL]
+    assert response.content == ""
+    call = fake.calls[0]
+    assert call["url"] == "https://chatgpt.com/backend-api/codex/responses"
+    assert call["headers"]["Authorization"] == "Bearer oauth-token"
+    assert call["headers"]["chatgpt-account-id"] == "acct-123"
+    assert call["headers"]["OpenAI-Beta"] == "responses=experimental"
+    assert call["headers"]["X-Test"] == "1"
+    body = call["json"]
+    assert body["model"] == "gpt-5.4"
+    assert body["instructions"] == "Generate an image based on the user's request."
+    assert body["input"] == [{"role": "user", "content": "draw a cat"}]
+    assert body["tools"] == [{"type": "image_generation"}]
+    assert body["tool_choice"] == "auto"
+    assert body["store"] is False
+    assert body["stream"] is True
+
+
+@pytest.mark.asyncio
+async def test_codex_strips_model_prefix(monkeypatch) -> None:
+    import sys
+    from dataclasses import dataclass
+    from types import SimpleNamespace
+
+    @dataclass
+    class FakeToken:
+        account_id: str = "acct-123"
+        access: str = "oauth-token"
+
+    async def fake_to_thread(fn, *args, **kwargs):
+        return fn(*args, **kwargs)
+
+    monkeypatch.setattr("asyncio.to_thread", fake_to_thread)
+    fake_oauth = SimpleNamespace(get_token=lambda: FakeToken())
+    monkeypatch.setitem(sys.modules, "oauth_cli_kit", fake_oauth)
+
+    fake = FakeClient(FakeResponse({}, sse_lines=[
+        f'data: {{"type":"response.output_item.done","item":{{"type":"image_generation_call","result":"{PNG_DATA_URL}"}}}}',
+        "",
+        'data: [DONE]',
+        "",
+    ]))
+    client = CodexImageGenerationClient(
+        api_key=None, client=fake  # type: ignore[arg-type]
+    )
+
+    await client.generate(prompt="draw", model="openai-codex/gpt-5.4")
+
+    assert fake.calls[0]["json"]["model"] == "gpt-5.4"
+
+
+@pytest.mark.asyncio
+async def test_codex_requires_oauth(monkeypatch) -> None:
+    async def fake_to_thread(fn, *args, **kwargs):
+        raise RuntimeError("no token")
+
+    monkeypatch.setattr("asyncio.to_thread", fake_to_thread)
+
+    client = CodexImageGenerationClient(api_key=None)
+
+    with pytest.raises(ImageGenerationError, match="OAuth token"):
+        await client.generate(prompt="draw", model="gpt-5.4")
+
+
+@pytest.mark.asyncio
+async def test_codex_no_images_raises(monkeypatch) -> None:
+    import sys
+    from dataclasses import dataclass
+    from types import SimpleNamespace
+
+    @dataclass
+    class FakeToken:
+        account_id: str = "acct-123"
+        access: str = "oauth-token"
+
+    async def fake_to_thread(fn, *args, **kwargs):
+        return fn(*args, **kwargs)
+
+    monkeypatch.setattr("asyncio.to_thread", fake_to_thread)
+    fake_oauth = SimpleNamespace(get_token=lambda: FakeToken())
+    monkeypatch.setitem(sys.modules, "oauth_cli_kit", fake_oauth)
+
+    fake = FakeClient(FakeResponse({}, sse_lines=[
+        'data: {"type":"response.completed","response":{"status":"completed"}}',
+        "",
+        'data: [DONE]',
+        "",
+    ]))
+    client = CodexImageGenerationClient(
+        api_key=None, client=fake  # type: ignore[arg-type]
+    )
+
+    with pytest.raises(ImageGenerationError, match="returned no images"):
+        await client.generate(prompt="draw", model="gpt-5.4")
+
+
+@pytest.mark.asyncio
+async def test_codex_extracts_text_content(monkeypatch) -> None:
+    import sys
+    from dataclasses import dataclass
+    from types import SimpleNamespace
+
+    @dataclass
+    class FakeToken:
+        account_id: str = "acct-123"
+        access: str = "oauth-token"
+
+    async def fake_to_thread(fn, *args, **kwargs):
+        return fn(*args, **kwargs)
+
+    monkeypatch.setattr("asyncio.to_thread", fake_to_thread)
+    fake_oauth = SimpleNamespace(get_token=lambda: FakeToken())
+    monkeypatch.setitem(sys.modules, "oauth_cli_kit", fake_oauth)
+
+    fake = FakeClient(FakeResponse({}, sse_lines=[
+        'data: {"type":"response.output_text.delta","delta":"Here "}',
+        "",
+        'data: {"type":"response.output_text.delta","delta":"is your cat image."}',
+        "",
+        f'data: {{"type":"response.output_item.done","item":{{"type":"image_generation_call","result":"{PNG_DATA_URL}"}}}}',
+        "",
+        'data: [DONE]',
+        "",
+    ]))
+    client = CodexImageGenerationClient(
+        api_key=None, client=fake  # type: ignore[arg-type]
+    )
+
+    response = await client.generate(prompt="draw a cat", model="gpt-5.4")
+
+    assert response.images == [PNG_DATA_URL]
+    assert response.content == "Here is your cat image."
+
+
+@pytest.mark.asyncio
+async def test_codex_json_result_format(monkeypatch) -> None:
+    """image_generation_call result can be a dict with image_url key."""
+    import sys
+    from dataclasses import dataclass
+    from types import SimpleNamespace
+
+    @dataclass
+    class FakeToken:
+        account_id: str = "acct-123"
+        access: str = "oauth-token"
+
+    async def fake_to_thread(fn, *args, **kwargs):
+        return fn(*args, **kwargs)
+
+    monkeypatch.setattr("asyncio.to_thread", fake_to_thread)
+    fake_oauth = SimpleNamespace(get_token=lambda: FakeToken())
+    monkeypatch.setitem(sys.modules, "oauth_cli_kit", fake_oauth)
+
+    fake = FakeClient(FakeResponse({}, sse_lines=[
+        f'data: {{"type":"response.output_item.done","item":{{"type":"image_generation_call","result":{{"image_url":"{PNG_DATA_URL}"}}}}}}',
+        "",
+        'data: [DONE]',
+        "",
+    ]))
+    client = CodexImageGenerationClient(
+        api_key=None, client=fake  # type: ignore[arg-type]
+    )
+
+    response = await client.generate(prompt="draw", model="gpt-5.4")
+
+    assert response.images == [PNG_DATA_URL]
+
+
+@pytest.mark.asyncio
+async def test_openai_no_images_raises() -> None:
+    fake = FakeClient(FakeResponse({"data": []}))
+    client = OpenAIImageGenerationClient(
+        api_key="sk-openai-test",
+        client=fake,  # type: ignore[arg-type]
+    )
+
+    with pytest.raises(ImageGenerationError, match="returned no images"):
+        await client.generate(prompt="draw", model="dall-e-3")

tests/providers/test_litellm_kwargs.py

@@ -441,6 +441,15 @@ def test_openrouter_spec_is_gateway() -> None:
     assert spec.default_api_base == "https://openrouter.ai/api/v1"
 
 
+def test_novita_spec_uses_openai_compatible_gateway() -> None:
+    spec = find_by_name("novita")
+    assert spec is not None
+    assert spec.is_gateway is True
+    assert spec.backend == "openai_compat"
+    assert spec.env_key == "NOVITA_API_KEY"
+    assert spec.default_api_base == "https://api.novita.ai/openai"
+
+
 def test_gemma_routes_to_gemini_provider() -> None:
     """gemma models (e.g. gemma-3-27b-it) must auto-route to Gemini when GEMINI_API_KEY is set.
     Users running gemma via the Gemini API endpoint expect automatic provider detection."""
@@ -1013,6 +1022,41 @@ def test_openai_compat_keeps_tool_calls_after_consecutive_assistant_messages() -
     assert sanitized[2]["tool_call_id"] == "3ec83c30d"
 
 
+def test_openai_compat_deduplicates_duplicate_tool_call_ids_in_history() -> None:
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
+        provider = OpenAICompatProvider()
+
+    sanitized = provider._sanitize_messages([
+        {"role": "user", "content": "check both files"},
+        {
+            "role": "assistant",
+            "content": "",
+            "tool_calls": [
+                {
+                    "id": "ab1b45c2a",
+                    "type": "function",
+                    "function": {"name": "read_file", "arguments": '{"path":"a.txt"}'},
+                },
+                {
+                    "id": "ab1b45c2a",
+                    "type": "function",
+                    "function": {"name": "read_file", "arguments": '{"path":"b.txt"}'},
+                },
+            ],
+        },
+        {"role": "tool", "tool_call_id": "ab1b45c2a", "name": "read_file", "content": "a"},
+        {"role": "tool", "tool_call_id": "ab1b45c2a", "name": "read_file", "content": "b"},
+        {"role": "user", "content": "continue"},
+    ])
+
+    tool_call_ids = [tc["id"] for tc in sanitized[1]["tool_calls"]]
+    tool_result_ids = [sanitized[2]["tool_call_id"], sanitized[3]["tool_call_id"]]
+
+    assert tool_call_ids[0] == "ab1b45c2a"
+    assert len(tool_call_ids) == len(set(tool_call_ids)) == 2
+    assert tool_result_ids == tool_call_ids
+
+
 def test_openai_compat_stringifies_dict_tool_arguments() -> None:
     with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
         provider = OpenAICompatProvider()
@@ -1382,12 +1426,15 @@ def test_kimi_k25_thinking_enabled() -> None:
     """kimi-k2.5 with reasoning_effort set should opt in to thinking."""
     kw = _build_kwargs_for("moonshot", "kimi-k2.5", reasoning_effort="medium")
     assert kw.get("extra_body") == {"thinking": {"type": "enabled"}}
+    # Moonshot rejects both 'reasoning_effort' and 'thinking' (#3939)
+    assert "reasoning_effort" not in kw
 
 
 def test_kimi_k25_thinking_disabled_for_minimal() -> None:
     """reasoning_effort='minimal' maps to thinking disabled for kimi-k2.5."""
     kw = _build_kwargs_for("moonshot", "kimi-k2.5", reasoning_effort="minimal")
     assert kw.get("extra_body") == {"thinking": {"type": "disabled"}}
+    assert "reasoning_effort" not in kw
 
 
 def test_kimi_k25_no_extra_body_when_reasoning_effort_none() -> None:
@@ -1397,21 +1444,36 @@ def test_kimi_k25_no_extra_body_when_reasoning_effort_none() -> None:
 
 
 def test_kimi_k25_thinking_enabled_with_openrouter_prefix() -> None:
-    """OpenRouter-style model names like moonshotai/kimi-k2.5 must trigger thinking."""
+    """OpenRouter-style model names like moonshotai/kimi-k2.5 must trigger thinking.
+
+    OR drops upstream-provider `thinking` fields, so the same intent also has
+    to go through OR's `reasoning.effort` shape (#3851 follow-up).
+    """
     kw = _build_kwargs_for("openrouter", "moonshotai/kimi-k2.5", reasoning_effort="medium")
-    assert kw.get("extra_body") == {"thinking": {"type": "enabled"}}
+    assert kw.get("extra_body") == {
+        "thinking": {"type": "enabled"},
+        "reasoning": {"effort": "medium"},
+    }
+    # Even via OR, reasoning_effort wire kwarg is dropped for kimi models
+    assert "reasoning_effort" not in kw
 
 
 def test_kimi_k26_thinking_enabled() -> None:
     """kimi-k2.6 with reasoning_effort set should opt in to thinking."""
     kw = _build_kwargs_for("moonshot", "kimi-k2.6", reasoning_effort="medium")
     assert kw.get("extra_body") == {"thinking": {"type": "enabled"}}
+    assert "reasoning_effort" not in kw
 
 
 def test_kimi_k26_thinking_enabled_with_openrouter_prefix() -> None:
-    """OpenRouter-style names like moonshotai/kimi-k2.6 must trigger thinking."""
+    """OpenRouter-style names like moonshotai/kimi-k2.6 must trigger thinking
+    via both upstream `thinking` and OR's `reasoning.effort`."""
     kw = _build_kwargs_for("openrouter", "moonshotai/kimi-k2.6", reasoning_effort="medium")
-    assert kw.get("extra_body") == {"thinking": {"type": "enabled"}}
+    assert kw.get("extra_body") == {
+        "thinking": {"type": "enabled"},
+        "reasoning": {"effort": "medium"},
+    }
+    assert "reasoning_effort" not in kw
 
 
 def test_moonshot_kimi_k26_temperature_override() -> None:
@@ -1430,6 +1492,7 @@ def test_kimi_k26_code_preview_thinking_enabled() -> None:
     """k2.6-code-preview also supports thinking; should behave like k2.5."""
     kw = _build_kwargs_for("moonshot", "k2.6-code-preview", reasoning_effort="high")
     assert kw.get("extra_body") == {"thinking": {"type": "enabled"}}
+    assert "reasoning_effort" not in kw
 
 
 def test_kimi_k2_series_no_thinking_injection() -> None:
@@ -1459,6 +1522,7 @@ def test_kimi_k25_thinking_disabled_for_none_string() -> None:
     """reasoning_effort='none' maps to thinking disabled for kimi-k2.5."""
     kw = _build_kwargs_for("moonshot", "kimi-k2.5", reasoning_effort="none")
     assert kw.get("extra_body") == {"thinking": {"type": "disabled"}}
+    assert "reasoning_effort" not in kw
 
 
 def test_dashscope_thinking_disabled_for_none_string() -> None:

tests/providers/test_novita_provider.py

@@ -0,0 +1,97 @@
+"""Tests for the Novita AI provider registration."""
+
+from unittest.mock import patch
+
+from nanobot.config.schema import Config, ProvidersConfig
+from nanobot.providers.openai_compat_provider import OpenAICompatProvider
+from nanobot.providers.registry import PROVIDERS, find_by_name
+
+
+def test_novita_config_field_exists() -> None:
+    config = ProvidersConfig()
+
+    assert hasattr(config, "novita")
+
+
+def test_novita_provider_in_registry() -> None:
+    specs = {spec.name: spec for spec in PROVIDERS}
+
+    assert "novita" in specs
+    novita = specs["novita"]
+    assert novita.backend == "openai_compat"
+    assert novita.env_key == "NOVITA_API_KEY"
+    assert novita.display_name == "Novita AI"
+    assert novita.is_gateway is True
+    assert novita.detect_by_base_keyword == "novita"
+    assert novita.default_api_base == "https://api.novita.ai/openai"
+    assert novita.strip_model_prefix is False
+
+
+def test_find_by_name_novita() -> None:
+    spec = find_by_name("novita")
+
+    assert spec is not None
+    assert spec.name == "novita"
+
+
+def test_novita_forced_provider_uses_default_api_base() -> None:
+    config = Config.model_validate({
+        "providers": {
+            "novita": {
+                "apiKey": "novita-key",
+            },
+        },
+        "agents": {
+            "defaults": {
+                "model": "deepseek-v4-pro",
+                "provider": "novita",
+            },
+        },
+    })
+
+    assert config.get_provider_name("deepseek-v4-pro") == "novita"
+    assert config.get_api_key("deepseek-v4-pro") == "novita-key"
+    assert config.get_api_base("deepseek-v4-pro") == "https://api.novita.ai/openai"
+
+
+def test_novita_gateway_routes_unprefixed_models_when_configured() -> None:
+    config = Config.model_validate({
+        "providers": {
+            "novita": {
+                "apiKey": "novita-key",
+            },
+        },
+        "agents": {
+            "defaults": {
+                "model": "deepseek-v4-pro",
+            },
+        },
+    })
+
+    assert config.get_provider_name("deepseek-v4-pro") == "novita"
+    assert config.get_api_key("deepseek-v4-pro") == "novita-key"
+    assert config.get_api_base("deepseek-v4-pro") == "https://api.novita.ai/openai"
+
+
+def test_novita_preserves_model_api_id() -> None:
+    spec = find_by_name("novita")
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
+        provider = OpenAICompatProvider(
+            api_key="novita-key",
+            default_model="deepseek-v4-pro",
+            spec=spec,
+        )
+
+    kwargs = provider._build_kwargs(
+        messages=[{"role": "user", "content": "hi"}],
+        tools=None,
+        model="deepseek-v4-pro",
+        max_tokens=1024,
+        temperature=0.7,
+        reasoning_effort=None,
+        tool_choice=None,
+    )
+
+    assert kwargs["model"] == "deepseek-v4-pro"
+    assert kwargs["max_tokens"] == 1024
+    assert "max_completion_tokens" not in kwargs

tests/providers/test_openai_responses.py

@@ -155,6 +155,49 @@ class TestConvertMessages:
         assert items[0]["id"] == "fc_1"
         assert items[0]["name"] == "get_weather"
 
+    def test_duplicate_response_item_ids_are_made_unique(self):
+        """Codex rejects replayed Responses input items with duplicate ids."""
+        _, items = convert_messages([
+            {
+                "role": "assistant",
+                "content": None,
+                "tool_calls": [{
+                    "id": "call_a|rs_same",
+                    "function": {"name": "first", "arguments": "{}"},
+                }],
+            },
+            {"role": "tool", "tool_call_id": "call_a|rs_same", "content": "ok"},
+            {
+                "role": "assistant",
+                "content": None,
+                "tool_calls": [{
+                    "id": "call_b|rs_same",
+                    "function": {"name": "second", "arguments": "{}"},
+                }],
+            },
+            {"role": "tool", "tool_call_id": "call_b|rs_same", "content": "ok"},
+        ])
+        function_call_ids = [
+            item["id"] for item in items if item.get("type") == "function_call"
+        ]
+        assert function_call_ids == ["rs_same", "rs_same_2"]
+        assert len(function_call_ids) == len(set(function_call_ids))
+
+    def test_fallback_response_item_ids_are_unique_with_multiple_tool_calls(self):
+        _, items = convert_messages([{
+            "role": "assistant",
+            "content": None,
+            "tool_calls": [
+                {"id": "call_a", "function": {"name": "first", "arguments": "{}"}},
+                {"id": "call_b", "function": {"name": "second", "arguments": "{}"}},
+            ],
+        }])
+        function_call_ids = [
+            item["id"] for item in items if item.get("type") == "function_call"
+        ]
+        assert function_call_ids == ["fc_0", "fc_0_2"]
+        assert len(function_call_ids) == len(set(function_call_ids))
+
     def test_assistant_with_tool_calls_no_id(self):
         """Fallback IDs when tool_call.id is missing."""
         _, items = convert_messages([{

tests/providers/test_xiaomi_mimo_thinking.py

@@ -32,7 +32,7 @@ def _mimo_spec():
 
 
 def _openrouter_spec():
-    """Return the registered OpenRouter ProviderSpec (no thinking_style)."""
+    """Return the registered OpenRouter ProviderSpec."""
     specs = {s.name: s for s in PROVIDERS}
     return specs["openrouter"]
 
@@ -77,6 +77,13 @@ def test_xiaomi_mimo_uses_thinking_type_style():
     assert spec.default_api_base == "https://api.xiaomimimo.com/v1"
 
 
+def test_openrouter_declares_gateway_reasoning_style():
+    """OpenRouter uses its own reasoning.effort field for routed thinking models."""
+    spec = _openrouter_spec()
+    assert spec.thinking_style == ""
+    assert spec.gateway_reasoning_style == "reasoning_effort"
+
+
 # ---------------------------------------------------------------------------
 # _build_kwargs wire-format
 # ---------------------------------------------------------------------------
@@ -142,9 +149,11 @@ def test_mimo_reasoning_effort_unset_preserves_provider_default():
 
 
 def test_mimo_via_openrouter_reasoning_effort_none_disables_thinking():
-    """OpenRouter routes MiMo as "xiaomi/mimo-v2.5-pro"; the openrouter spec
-    has no thinking_style, so the disable signal must come from the
-    model-name path (#3845)."""
+    """OpenRouter routes MiMo as "xiaomi/mimo-v2.5-pro" and does NOT forward
+    extra_body.thinking to upstream, so a disable signal must also reach OR
+    in its own `reasoning.effort` shape. Verifies both the upstream-MiMo
+    payload (#3845) and the OR-native payload (#3851 follow-up) are sent.
+    """
     provider = _openrouter_provider("xiaomi/mimo-v2.5-pro")
     kwargs = provider._build_kwargs(
         messages=_simple_messages(),
@@ -152,11 +161,15 @@ def test_mimo_via_openrouter_reasoning_effort_none_disables_thinking():
         temperature=0.7, reasoning_effort="none", tool_choice=None,
     )
     assert "reasoning_effort" not in kwargs
-    assert kwargs["extra_body"] == {"thinking": {"type": "disabled"}}
+    assert kwargs["extra_body"] == {
+        "thinking": {"type": "disabled"},
+        "reasoning": {"effort": "none"},
+    }
 
 
 def test_mimo_via_openrouter_reasoning_effort_medium_enables_thinking():
-    """Same as the direct path: any non-none/minimal effort enables thinking."""
+    """Non-none/minimal effort enables thinking and the OR `reasoning.effort`
+    field mirrors the requested effort level."""
     provider = _openrouter_provider("xiaomi/mimo-v2.5-pro")
     kwargs = provider._build_kwargs(
         messages=_simple_messages(),
@@ -164,7 +177,10 @@ def test_mimo_via_openrouter_reasoning_effort_medium_enables_thinking():
         temperature=0.7, reasoning_effort="medium", tool_choice=None,
     )
     assert kwargs.get("reasoning_effort") == "medium"
-    assert kwargs["extra_body"] == {"thinking": {"type": "enabled"}}
+    assert kwargs["extra_body"] == {
+        "thinking": {"type": "enabled"},
+        "reasoning": {"effort": "medium"},
+    }
 
 
 def test_mimo_via_openrouter_bare_slug_also_matches():
@@ -176,12 +192,16 @@ def test_mimo_via_openrouter_bare_slug_also_matches():
         tools=None, model=None, max_tokens=100,
         temperature=0.7, reasoning_effort="none", tool_choice=None,
     )
-    assert kwargs["extra_body"] == {"thinking": {"type": "disabled"}}
+    assert kwargs["extra_body"] == {
+        "thinking": {"type": "disabled"},
+        "reasoning": {"effort": "none"},
+    }
 
 
 def test_mimo_flash_via_openrouter_does_not_inject_thinking():
     """mimo-v2-flash has no thinking mode per Xiaomi docs; the allowlist
-    excludes it, so no thinking field should be injected on the gateway path."""
+    excludes it, so neither the upstream `thinking` field nor OR's
+    `reasoning.effort` should be injected on the gateway path."""
     provider = _openrouter_provider("xiaomi/mimo-v2-flash")
     kwargs = provider._build_kwargs(
         messages=_simple_messages(),
@@ -200,3 +220,18 @@ def test_non_mimo_model_via_openrouter_unaffected():
         temperature=0.7, reasoning_effort="none", tool_choice=None,
     )
     assert "extra_body" not in kwargs
+
+
+def test_kimi_via_openrouter_also_injects_reasoning_effort():
+    """Kimi has the same gateway problem as MiMo: OR drops the upstream
+    `thinking` field. The same OR-reasoning injection should fire."""
+    provider = _openrouter_provider("moonshotai/kimi-k2.5")
+    kwargs = provider._build_kwargs(
+        messages=_simple_messages(),
+        tools=None, model=None, max_tokens=100,
+        temperature=0.7, reasoning_effort="none", tool_choice=None,
+    )
+    assert kwargs["extra_body"] == {
+        "thinking": {"type": "disabled"},
+        "reasoning": {"effort": "none"},
+    }

tests/tools/test_apply_patch_tool.py

@@ -0,0 +1,330 @@
+from __future__ import annotations
+
+import asyncio
+
+from nanobot.agent.tools.apply_patch import ApplyPatchTool
+
+
+def test_apply_patch_edits_replace(tmp_path):
+    target = tmp_path / "calc.py"
+    target.write_text("def add(a, b):\n    return a + b\n")
+    tool = ApplyPatchTool(workspace=tmp_path)
+
+    result = asyncio.run(
+        tool.execute(
+            edits=[
+                {
+                    "path": "calc.py",
+                    "action": "replace",
+                    "old_text": "    return a + b",
+                    "new_text": "    return a - b",
+                }
+            ]
+        )
+    )
+
+    assert "update calc.py" in result
+    assert target.read_text() == "def add(a, b):\n    return a - b\n"
+
+
+def test_apply_patch_edits_add_new_file(tmp_path):
+    tool = ApplyPatchTool(workspace=tmp_path)
+
+    result = asyncio.run(
+        tool.execute(
+            edits=[
+                {
+                    "path": "config.py",
+                    "action": "add",
+                    "new_text": "DEBUG = True",
+                }
+            ]
+        )
+    )
+
+    assert "add config.py" in result
+    assert (tmp_path / "config.py").read_text() == "DEBUG = True\n"
+
+
+def test_apply_patch_edits_preserves_new_file_trailing_blank_lines(tmp_path):
+    tool = ApplyPatchTool(workspace=tmp_path)
+
+    result = asyncio.run(
+        tool.execute(
+            edits=[
+                {
+                    "path": "notes.txt",
+                    "action": "add",
+                    "new_text": "one\n\n",
+                }
+            ]
+        )
+    )
+
+    assert "add notes.txt" in result
+    assert (tmp_path / "notes.txt").read_text() == "one\n\n"
+
+
+def test_apply_patch_edits_add_to_existing_file(tmp_path):
+    target = tmp_path / "log.py"
+    target.write_text("import logging\n\nlogger = logging.getLogger(__name__)\n")
+    tool = ApplyPatchTool(workspace=tmp_path)
+
+    result = asyncio.run(
+        tool.execute(
+            edits=[
+                {
+                    "path": "log.py",
+                    "action": "add",
+                    "new_text": "def debug(msg):\n    logger.debug(msg)",
+                }
+            ]
+        )
+    )
+
+    assert "update log.py" in result
+    assert (
+        target.read_text()
+        == "import logging\n\nlogger = logging.getLogger(__name__)\ndef debug(msg):\n    logger.debug(msg)\n"
+    )
+
+
+def test_apply_patch_edits_delete(tmp_path):
+    target = tmp_path / "utils.py"
+    target.write_text("def unused():\n    pass\ndef used():\n    return 1\n")
+    tool = ApplyPatchTool(workspace=tmp_path)
+
+    result = asyncio.run(
+        tool.execute(
+            edits=[
+                {
+                    "path": "utils.py",
+                    "action": "delete",
+                    "old_text": "def unused():\n    pass\n",
+                }
+            ]
+        )
+    )
+
+    assert "update utils.py" in result
+    assert target.read_text() == "def used():\n    return 1\n"
+
+
+def test_apply_patch_edits_delete_entire_file(tmp_path):
+    target = tmp_path / "obsolete.txt"
+    target.write_text("remove me\n")
+    tool = ApplyPatchTool(workspace=tmp_path)
+
+    result = asyncio.run(
+        tool.execute(
+            edits=[
+                {
+                    "path": "obsolete.txt",
+                    "action": "delete",
+                    "old_text": "remove me\n",
+                }
+            ]
+        )
+    )
+
+    assert "delete obsolete.txt" in result
+    assert not target.exists()
+
+
+def test_apply_patch_edits_delete_substring_with_surrounding_whitespace(tmp_path):
+    target = tmp_path / "keep_whitespace.txt"
+    target.write_text("  token  \n")
+    tool = ApplyPatchTool(workspace=tmp_path)
+
+    result = asyncio.run(
+        tool.execute(
+            edits=[
+                {
+                    "path": "keep_whitespace.txt",
+                    "action": "delete",
+                    "old_text": "token",
+                }
+            ]
+        )
+    )
+
+    assert "update keep_whitespace.txt" in result
+    assert target.exists()
+    assert target.read_text() == "    \n"
+
+
+def test_apply_patch_edits_batch_multiple_files(tmp_path):
+    a = tmp_path / "a.py"
+    a.write_text("X = 1\n")
+    b = tmp_path / "b.py"
+    b.write_text("from a import X\nprint(X)\n")
+    tool = ApplyPatchTool(workspace=tmp_path)
+
+    result = asyncio.run(
+        tool.execute(
+            edits=[
+                {
+                    "path": "a.py",
+                    "action": "replace",
+                    "old_text": "X = 1",
+                    "new_text": "Y = 1",
+                },
+                {
+                    "path": "b.py",
+                    "action": "replace",
+                    "old_text": "from a import X",
+                    "new_text": "from a import Y",
+                },
+            ]
+        )
+    )
+
+    assert "update a.py" in result
+    assert "update b.py" in result
+    assert a.read_text() == "Y = 1\n"
+    assert b.read_text() == "from a import Y\nprint(X)\n"
+
+
+def test_apply_patch_edits_rejects_ambiguous_old_text(tmp_path):
+    target = tmp_path / "repeated.txt"
+    target.write_text("target\nmiddle\ntarget\n")
+    tool = ApplyPatchTool(workspace=tmp_path)
+
+    result = asyncio.run(
+        tool.execute(
+            edits=[
+                {
+                    "path": "repeated.txt",
+                    "action": "replace",
+                    "old_text": "target",
+                    "new_text": "changed",
+                }
+            ]
+        )
+    )
+
+    assert "old_text appears multiple times" in result
+    assert target.read_text() == "target\nmiddle\ntarget\n"
+
+
+def test_apply_patch_edits_dry_run_validates_without_writing(tmp_path):
+    target = tmp_path / "dry.txt"
+    target.write_text("before\n")
+    tool = ApplyPatchTool(workspace=tmp_path)
+
+    result = asyncio.run(
+        tool.execute(
+            edits=[
+                {
+                    "path": "dry.txt",
+                    "action": "replace",
+                    "old_text": "before",
+                    "new_text": "after",
+                },
+                {
+                    "path": "added.txt",
+                    "action": "add",
+                    "new_text": "new",
+                },
+            ],
+            dry_run=True,
+        )
+    )
+
+    assert "Patch dry-run succeeded" in result
+    assert target.read_text() == "before\n"
+    assert not (tmp_path / "added.txt").exists()
+
+
+def test_apply_patch_edits_rejects_absolute_and_parent_paths(tmp_path):
+    tool = ApplyPatchTool(workspace=tmp_path)
+
+    absolute = asyncio.run(
+        tool.execute(
+            edits=[
+                {
+                    "path": "/tmp/owned.txt",
+                    "action": "add",
+                    "new_text": "nope",
+                }
+            ]
+        )
+    )
+    parent = asyncio.run(
+        tool.execute(
+            edits=[
+                {
+                    "path": "../owned.txt",
+                    "action": "add",
+                    "new_text": "nope",
+                }
+            ]
+        )
+    )
+    windows_absolute = asyncio.run(
+        tool.execute(
+            edits=[
+                {
+                    "path": r"C:\owned.txt",
+                    "action": "add",
+                    "new_text": "nope",
+                }
+            ]
+        )
+    )
+    windows_parent = asyncio.run(
+        tool.execute(
+            edits=[
+                {
+                    "path": r"..\owned.txt",
+                    "action": "add",
+                    "new_text": "nope",
+                }
+            ]
+        )
+    )
+
+    assert "must be relative" in absolute
+    assert "must not contain '..'" in parent
+    assert "must be relative" in windows_absolute
+    assert "must not contain '..'" in windows_parent
+    assert not (tmp_path.parent / "owned.txt").exists()
+
+
+def test_apply_patch_edits_reports_invalid_edit_shapes(tmp_path):
+    tool = ApplyPatchTool(workspace=tmp_path)
+
+    missing_path = asyncio.run(tool.execute(edits=[{"action": "add", "new_text": "x"}]))
+    missing_action = asyncio.run(tool.execute(edits=[{"path": "x.txt", "new_text": "x"}]))
+    non_object = asyncio.run(tool.execute(edits=["not an object"]))  # type: ignore[list-item]
+
+    assert "path required for edit" in missing_path
+    assert "action required for edit: x.txt" in missing_action
+    assert "each edit must be an object" in non_object
+
+
+def test_apply_patch_edits_rolls_back_when_late_operation_fails(tmp_path):
+    first = tmp_path / "first.txt"
+    first.write_text("before\n")
+    tool = ApplyPatchTool(workspace=tmp_path)
+
+    result = asyncio.run(
+        tool.execute(
+            edits=[
+                {
+                    "path": "first.txt",
+                    "action": "replace",
+                    "old_text": "before",
+                    "new_text": "after",
+                },
+                {
+                    "path": "missing.txt",
+                    "action": "delete",
+                    "old_text": "remove me",
+                },
+            ]
+        )
+    )
+
+    assert "file to update does not exist: missing.txt" in result
+    assert first.read_text() == "before\n"

tests/tools/test_edit_enhancements.py

@@ -1,5 +1,5 @@
 """Tests for EditFileTool enhancements: read-before-edit tracking, path suggestions,
-.ipynb detection, and create-file semantics."""
+notebook JSON editing, and create-file semantics."""
 
 import pytest
 
@@ -108,22 +108,27 @@ class TestEditCreateFile:
 
 
 # ---------------------------------------------------------------------------
-# .ipynb detection
+# .ipynb editing
 # ---------------------------------------------------------------------------
 
-class TestEditIpynbDetection:
-    """edit_file should refuse .ipynb and suggest notebook_edit."""
+class TestEditIpynbFiles:
+    """edit_file edits notebooks as normal JSON files."""
 
     @pytest.fixture()
     def tool(self, tmp_path):
         return EditFileTool(workspace=tmp_path)
 
     @pytest.mark.asyncio
-    async def test_ipynb_rejected_with_suggestion(self, tool, tmp_path):
+    async def test_ipynb_can_be_edited_as_json(self, tool, tmp_path):
         f = tmp_path / "analysis.ipynb"
         f.write_text('{"cells": []}', encoding="utf-8")
-        result = await tool.execute(path=str(f), old_text="x", new_text="y")
-        assert "notebook" in result.lower()
+        result = await tool.execute(
+            path=str(f),
+            old_text='"cells": []',
+            new_text='"cells": [{"cell_type": "markdown", "source": "hi"}]',
+        )
+        assert "Successfully edited" in result
+        assert '"source": "hi"' in f.read_text(encoding="utf-8")
 
 
 # ---------------------------------------------------------------------------

tests/tools/test_exec_platform.py

@@ -162,7 +162,7 @@ class TestPathAppendPlatform:
         captured_cmd = None
         captured_env = {}
 
-        async def capture_spawn(cmd, cwd, env):
+        async def capture_spawn(cmd, cwd, env, shell_program=None, login=True):
             nonlocal captured_cmd
             captured_cmd = cmd
             captured_env.update(env)
@@ -190,7 +190,7 @@ class TestPathAppendPlatform:
 
         captured_env = {}
 
-        async def capture_spawn(cmd, cwd, env):
+        async def capture_spawn(cmd, cwd, env, shell_program=None, login=True):
             captured_env.update(env)
             return mock_proc
 

tests/tools/test_exec_session_tools.py

@@ -0,0 +1,361 @@
+from __future__ import annotations
+
+import asyncio
+import re
+import shlex
+import subprocess
+import sys
+
+from nanobot.agent.tools.shell import ExecTool
+from nanobot.agent.tools.exec_session import ExecSessionManager, ListExecSessionsTool, WriteStdinTool
+
+
+def _python_command(code: str) -> str:
+    if sys.platform == "win32":
+        return f"{subprocess.list2cmdline([sys.executable])} -u -c {subprocess.list2cmdline([code])}"
+    return f"{shlex.quote(sys.executable)} -u -c {shlex.quote(code)}"
+
+
+def _session_id(output: str) -> str:
+    match = re.search(r"session_id:\s*([0-9a-f]+)", output)
+    assert match, output
+    return match.group(1)
+
+
+def test_exec_keeps_one_shot_behavior_without_yield_time_ms(tmp_path):
+    async def run() -> str:
+        tool = ExecTool(working_dir=str(tmp_path), timeout=5)
+        return await tool.execute(command="echo hello")
+
+    result = asyncio.run(run())
+
+    assert "hello" in result
+    assert "Exit code: 0" in result
+    assert "session_id:" not in result
+
+
+def test_exec_accepts_command_aliases(tmp_path):
+    async def run() -> str:
+        tool = ExecTool(working_dir="/")
+        return await tool.execute(
+            cmd=_python_command("import os; print(os.getcwd())"),
+            workdir=str(tmp_path),
+        )
+
+    result = asyncio.run(run())
+
+    assert str(tmp_path) in result
+    assert "Exit code: 0" in result
+
+
+def test_exec_returns_completed_session_output_when_yield_time_ms_is_used(tmp_path):
+    async def run() -> str:
+        manager = ExecSessionManager()
+        tool = ExecTool(working_dir=str(tmp_path), timeout=5, session_manager=manager)
+        stdin_tool = WriteStdinTool(manager=manager)
+
+        result = await tool.execute(command="echo hello", yield_time_ms=1000)
+        if "session_id:" in result:
+            sid = _session_id(result)
+            result += "\n" + await stdin_tool.execute(
+                session_id=sid,
+                chars="",
+                yield_time_ms=1000,
+            )
+        return result
+
+    result = asyncio.run(run())
+
+    assert "hello" in result
+    assert "Exit code: 0" in result
+    assert "session_id:" not in result
+
+
+def test_exec_session_accepts_max_output_tokens_alias(tmp_path):
+    async def run() -> str:
+        manager = ExecSessionManager()
+        tool = ExecTool(working_dir=str(tmp_path), timeout=5, session_manager=manager)
+        command = _python_command("print('A' * 2000)")
+        return await tool.execute(
+            command=command,
+            yield_time_ms=1000,
+            max_output_tokens=1000,
+        )
+
+    result = asyncio.run(run())
+
+    assert "chars truncated" in result
+    assert "Exit code: 0" in result
+
+
+def test_exec_one_shot_accepts_max_output_tokens_alias(tmp_path):
+    async def run() -> str:
+        tool = ExecTool(working_dir=str(tmp_path), timeout=5)
+        command = _python_command("print('A' * 2000)")
+        return await tool.execute(command=command, max_output_tokens=1000)
+
+    result = asyncio.run(run())
+
+    assert "chars truncated" in result
+    assert "Exit code: 0" in result
+
+
+def test_exec_accepts_supported_shell_parameter(tmp_path):
+    async def run() -> str:
+        tool = ExecTool(working_dir=str(tmp_path), timeout=5)
+        return await tool.execute(command="echo shell-ok", shell="sh", login=False)
+
+    if sys.platform == "win32":
+        return
+    result = asyncio.run(run())
+
+    assert "shell-ok" in result
+    assert "Exit code: 0" in result
+
+
+def test_exec_rejects_unsupported_shell(tmp_path):
+    async def run() -> str:
+        tool = ExecTool(working_dir=str(tmp_path), timeout=5)
+        return await tool.execute(command="echo no", shell="python")
+
+    if sys.platform == "win32":
+        return
+    result = asyncio.run(run())
+
+    assert "unsupported shell" in result
+
+
+def test_exec_can_continue_with_stdin(tmp_path):
+    async def run() -> tuple[str, str]:
+        manager = ExecSessionManager()
+        exec_tool = ExecTool(working_dir=str(tmp_path), timeout=5, session_manager=manager)
+        stdin_tool = WriteStdinTool(manager=manager)
+        command = _python_command(
+            "import sys; print('ready', flush=True); "
+            "line=sys.stdin.readline(); print('got:' + line.strip(), flush=True)"
+        )
+
+        initial = await exec_tool.execute(command=command, yield_time_ms=500)
+        sid = _session_id(initial)
+        result = await stdin_tool.execute(session_id=sid, chars="ping\n", yield_time_ms=1000)
+        return initial, result
+
+    initial, result = asyncio.run(run())
+    assert "ready" in initial
+    assert "Process running" in initial
+    assert "Elapsed:" in initial
+    assert "got:ping" in result
+    assert "Exit code: 0" in result
+    assert "Elapsed:" in result
+
+
+def test_write_stdin_can_close_stdin(tmp_path):
+    async def run() -> tuple[str, str]:
+        manager = ExecSessionManager()
+        exec_tool = ExecTool(working_dir=str(tmp_path), timeout=5, session_manager=manager)
+        stdin_tool = WriteStdinTool(manager=manager)
+        command = _python_command(
+            "import sys; print('ready', flush=True); "
+            "data=sys.stdin.read(); print('got:' + data, flush=True)"
+        )
+
+        initial = await exec_tool.execute(command=command, yield_time_ms=500)
+        sid = _session_id(initial)
+        result = await stdin_tool.execute(
+            session_id=sid,
+            chars="payload",
+            close_stdin=True,
+            yield_time_ms=1000,
+        )
+        return initial, result
+
+    initial, result = asyncio.run(run())
+    assert "ready" in initial
+    assert "got:payload" in result
+    assert "Stdin closed." in result
+    assert "Exit code: 0" in result
+
+
+def test_write_stdin_can_terminate_session(tmp_path):
+    async def run() -> tuple[str, str]:
+        manager = ExecSessionManager()
+        exec_tool = ExecTool(working_dir=str(tmp_path), timeout=30, session_manager=manager)
+        stdin_tool = WriteStdinTool(manager=manager)
+        command = _python_command(
+            "import time; print('ready', flush=True); time.sleep(30)"
+        )
+
+        initial = await exec_tool.execute(command=command, yield_time_ms=500)
+        sid = _session_id(initial)
+        result = await stdin_tool.execute(
+            session_id=sid,
+            terminate=True,
+            yield_time_ms=0,
+        )
+        return initial, result
+
+    initial, result = asyncio.run(run())
+    assert "ready" in initial
+    assert "Session terminated." in result
+    assert "Exit code:" in result
+
+
+def test_write_stdin_accepts_max_output_tokens_alias(tmp_path):
+    async def run() -> tuple[str, str, str]:
+        manager = ExecSessionManager()
+        exec_tool = ExecTool(working_dir=str(tmp_path), timeout=5, session_manager=manager)
+        stdin_tool = WriteStdinTool(manager=manager)
+        command = _python_command(
+            "import time; print('A' * 2000, flush=True); time.sleep(5)"
+        )
+
+        initial = await exec_tool.execute(command=command, yield_time_ms=0)
+        sid = _session_id(initial)
+        poll = await stdin_tool.execute(
+            session_id=sid,
+            yield_time_ms=500,
+            max_output_tokens=1000,
+        )
+        cleanup = await stdin_tool.execute(session_id=sid, terminate=True, yield_time_ms=0)
+        return initial, poll, cleanup
+
+    initial, poll, cleanup = asyncio.run(run())
+    assert "Process running" in initial
+    assert "chars truncated" in poll
+    assert "Session terminated." in cleanup
+
+
+def test_write_stdin_preserves_completed_session_output_until_polled(tmp_path):
+    async def run() -> tuple[str, str]:
+        manager = ExecSessionManager()
+        exec_tool = ExecTool(working_dir=str(tmp_path), timeout=5, session_manager=manager)
+        stdin_tool = WriteStdinTool(manager=manager)
+        command = _python_command(
+            "import time; print('ready', flush=True); "
+            "time.sleep(1.0); print('done', flush=True)"
+        )
+
+        initial = await exec_tool.execute(command=command, yield_time_ms=300)
+        sid = _session_id(initial)
+        await asyncio.sleep(1.2)
+        final = await stdin_tool.execute(session_id=sid, chars="", yield_time_ms=0)
+        return initial, final
+
+    initial, final = asyncio.run(run())
+
+    assert "ready" in initial
+    assert "done" in final
+    assert "Exit code: 0" in final
+
+
+def test_write_stdin_can_wait_for_expected_output(tmp_path):
+    async def run() -> tuple[str, str, str]:
+        manager = ExecSessionManager()
+        exec_tool = ExecTool(working_dir=str(tmp_path), timeout=5, session_manager=manager)
+        stdin_tool = WriteStdinTool(manager=manager)
+        command = _python_command(
+            "import time; print('booting', flush=True); "
+            "time.sleep(0.4); print('ready', flush=True); time.sleep(5)"
+        )
+
+        initial = await exec_tool.execute(command=command, yield_time_ms=100)
+        sid = _session_id(initial)
+        waited = await stdin_tool.execute(
+            session_id=sid,
+            wait_for="ready",
+            wait_timeout_ms=3000,
+            yield_time_ms=0,
+        )
+        cleanup = await stdin_tool.execute(session_id=sid, terminate=True, yield_time_ms=0)
+        return initial, waited, cleanup
+
+    initial, waited, cleanup = asyncio.run(run())
+
+    assert "Process running" in initial
+    assert "booting" in initial + waited
+    assert "ready" in waited
+    assert "Wait target not observed" not in waited
+    assert "Session terminated." in cleanup
+
+
+def test_write_stdin_wait_for_reports_timeout_without_killing_session(tmp_path):
+    async def run() -> tuple[str, str, str]:
+        manager = ExecSessionManager()
+        exec_tool = ExecTool(working_dir=str(tmp_path), timeout=5, session_manager=manager)
+        stdin_tool = WriteStdinTool(manager=manager)
+        command = _python_command(
+            "import time; print('booting', flush=True); time.sleep(5)"
+        )
+
+        initial = await exec_tool.execute(command=command, yield_time_ms=100)
+        sid = _session_id(initial)
+        waited = await stdin_tool.execute(
+            session_id=sid,
+            wait_for="never-ready",
+            wait_timeout_ms=200,
+            yield_time_ms=0,
+        )
+        cleanup = await stdin_tool.execute(session_id=sid, terminate=True, yield_time_ms=0)
+        return initial, waited, cleanup
+
+    initial, waited, cleanup = asyncio.run(run())
+
+    assert "Process running" in initial
+    assert "booting" in initial + waited
+    assert "Process running" in waited
+    assert "Wait target not observed: 'never-ready'" in waited
+    assert "Session terminated." in cleanup
+
+
+def test_exec_session_mode_reuses_exec_safety_guard(tmp_path):
+    manager = ExecSessionManager()
+    tool = ExecTool(
+        working_dir=str(tmp_path),
+        deny_patterns=[r"echo\s+blocked"],
+        session_manager=manager,
+    )
+
+    result = asyncio.run(tool.execute(command="echo blocked", yield_time_ms=0))
+
+    assert "blocked by deny pattern" in result
+
+
+def test_write_stdin_reports_missing_session(tmp_path):
+    manager = ExecSessionManager()
+    tool = WriteStdinTool(manager=manager)
+
+    result = asyncio.run(tool.execute(session_id="missing", chars=""))
+
+    assert "exec session not found" in result
+
+
+def test_list_exec_sessions_reports_running_commands(tmp_path):
+    async def run() -> tuple[str, str, str]:
+        manager = ExecSessionManager()
+        exec_tool = ExecTool(working_dir=str(tmp_path), timeout=5, session_manager=manager)
+        list_tool = ListExecSessionsTool(manager=manager)
+        stdin_tool = WriteStdinTool(manager=manager)
+        command = _python_command(
+            "import time; print('ready', flush=True); time.sleep(5)"
+        )
+
+        initial = await exec_tool.execute(command=command, yield_time_ms=500)
+        sid = _session_id(initial)
+        listing = await list_tool.execute()
+        cleanup = await stdin_tool.execute(session_id=sid, terminate=True, yield_time_ms=0)
+        return sid, listing, cleanup
+
+    sid, listing, cleanup = asyncio.run(run())
+
+    assert sid in listing
+    assert "running" in listing
+    assert "elapsed=" in listing
+    assert "remaining=" in listing
+    assert str(tmp_path) in listing
+    assert "Session terminated." in cleanup
+
+
+def test_list_exec_sessions_reports_empty_state():
+    result = asyncio.run(ListExecSessionsTool(manager=ExecSessionManager()).execute())
+
+    assert result == "No active exec sessions."

tests/tools/test_file_edit_coding_enhancements.py

@@ -0,0 +1,216 @@
+from __future__ import annotations
+
+import asyncio
+
+from nanobot.agent.tools.filesystem import EditFileTool, ReadFileTool
+
+
+def test_read_file_force_bypasses_dedup(tmp_path):
+    target = tmp_path / "data.txt"
+    target.write_text("alpha\n")
+    tool = ReadFileTool(workspace=tmp_path)
+
+    first = asyncio.run(tool.execute(path=str(target)))
+    second = asyncio.run(tool.execute(path=str(target)))
+    forced = asyncio.run(tool.execute(path=str(target), force=True))
+
+    assert "alpha" in first
+    assert "unchanged" in second.lower()
+    assert "alpha" in forced
+    assert "unchanged" not in forced.lower()
+
+
+def test_edit_file_can_select_occurrence(tmp_path):
+    target = tmp_path / "duplicate.txt"
+    target.write_text("one\nsame\ntwo\nsame\n")
+    tool = EditFileTool(workspace=tmp_path)
+
+    result = asyncio.run(tool.execute(
+        path=str(target),
+        old_text="same",
+        new_text="changed",
+        occurrence=2,
+    ))
+
+    assert "Successfully edited" in result
+    assert target.read_text() == "one\nsame\ntwo\nchanged\n"
+
+
+def test_edit_file_expected_replacements_guards_replace_all(tmp_path):
+    target = tmp_path / "duplicate.txt"
+    target.write_text("same\nsame\n")
+    tool = EditFileTool(workspace=tmp_path)
+
+    result = asyncio.run(tool.execute(
+        path=str(target),
+        old_text="same",
+        new_text="changed",
+        replace_all=True,
+        expected_replacements=1,
+    ))
+
+    assert "expected 1 replacements but would make 2" in result
+    assert target.read_text() == "same\nsame\n"
+
+
+def test_edit_file_expected_replacements_allows_replace_all_when_count_matches(tmp_path):
+    target = tmp_path / "duplicate.txt"
+    target.write_text("same\nsame\n")
+    tool = EditFileTool(workspace=tmp_path)
+
+    result = asyncio.run(tool.execute(
+        path=str(target),
+        old_text="same",
+        new_text="changed",
+        replace_all=True,
+        expected_replacements=2,
+    ))
+
+    assert "Successfully edited" in result
+    assert target.read_text() == "changed\nchanged\n"
+
+
+def test_edit_file_can_select_nearest_line_hint(tmp_path):
+    target = tmp_path / "duplicate.txt"
+    target.write_text("one\nsame\ntwo\nsame\n")
+    tool = EditFileTool(workspace=tmp_path)
+
+    result = asyncio.run(tool.execute(
+        path=str(target),
+        old_text="same",
+        new_text="changed",
+        line_hint=4,
+    ))
+
+    assert "Successfully edited" in result
+    assert target.read_text() == "one\nsame\ntwo\nchanged\n"
+
+
+def test_edit_file_can_edit_ipynb_as_json(tmp_path):
+    target = tmp_path / "analysis.ipynb"
+    target.write_text('{"cells": []}')
+    tool = EditFileTool(workspace=tmp_path)
+
+    result = asyncio.run(tool.execute(
+        path=str(target),
+        old_text='"cells": []',
+        new_text='"cells": [{"cell_type": "markdown", "source": "hi"}]',
+    ))
+
+    assert "Successfully edited" in result
+    assert '"source": "hi"' in target.read_text()
+
+
+def test_edit_file_multiple_match_hint_mentions_occurrence(tmp_path):
+    target = tmp_path / "duplicate.txt"
+    target.write_text("same\nsame\n")
+    tool = EditFileTool(workspace=tmp_path)
+
+    result = asyncio.run(tool.execute(
+        path=str(target),
+        old_text="same",
+        new_text="changed",
+    ))
+
+    assert "old_text appears 2 times" in result
+    assert "occurrence" in result
+    assert target.read_text() == "same\nsame\n"
+
+
+def test_edit_file_rejects_ambiguous_line_hint(tmp_path):
+    target = tmp_path / "duplicate.txt"
+    target.write_text("same\nmiddle\nsame\n")
+    tool = EditFileTool(workspace=tmp_path)
+
+    result = asyncio.run(tool.execute(
+        path=str(target),
+        old_text="same",
+        new_text="changed",
+        line_hint=2,
+    ))
+
+    assert "line_hint 2 is ambiguous" in result
+    assert target.read_text() == "same\nmiddle\nsame\n"
+
+
+def test_edit_file_rejects_occurrence_with_replace_all(tmp_path):
+    target = tmp_path / "duplicate.txt"
+    target.write_text("same\nsame\n")
+    tool = EditFileTool(workspace=tmp_path)
+
+    result = asyncio.run(tool.execute(
+        path=str(target),
+        old_text="same",
+        new_text="changed",
+        occurrence=1,
+        replace_all=True,
+    ))
+
+    assert "occurrence cannot be used with replace_all" in result
+    assert target.read_text() == "same\nsame\n"
+
+
+def test_edit_file_rejects_line_hint_with_replace_all(tmp_path):
+    target = tmp_path / "duplicate.txt"
+    target.write_text("same\nsame\n")
+    tool = EditFileTool(workspace=tmp_path)
+
+    result = asyncio.run(tool.execute(
+        path=str(target),
+        old_text="same",
+        new_text="changed",
+        line_hint=1,
+        replace_all=True,
+    ))
+
+    assert "line_hint cannot be used with replace_all" in result
+    assert target.read_text() == "same\nsame\n"
+
+
+def test_edit_file_rejects_line_hint_with_occurrence(tmp_path):
+    target = tmp_path / "duplicate.txt"
+    target.write_text("same\nsame\n")
+    tool = EditFileTool(workspace=tmp_path)
+
+    result = asyncio.run(tool.execute(
+        path=str(target),
+        old_text="same",
+        new_text="changed",
+        occurrence=1,
+        line_hint=1,
+    ))
+
+    assert "line_hint cannot be used with occurrence" in result
+    assert target.read_text() == "same\nsame\n"
+
+
+def test_edit_file_rejects_zero_occurrence(tmp_path):
+    target = tmp_path / "duplicate.txt"
+    target.write_text("same\n")
+    tool = EditFileTool(workspace=tmp_path)
+
+    result = asyncio.run(tool.execute(
+        path=str(target),
+        old_text="same",
+        new_text="changed",
+        occurrence=0,
+    ))
+
+    assert "occurrence must be >= 1" in result
+    assert target.read_text() == "same\n"
+
+
+def test_edit_file_rejects_zero_line_hint(tmp_path):
+    target = tmp_path / "duplicate.txt"
+    target.write_text("same\n")
+    tool = EditFileTool(workspace=tmp_path)
+
+    result = asyncio.run(tool.execute(
+        path=str(target),
+        old_text="same",
+        new_text="changed",
+        line_hint=0,
+    ))
+
+    assert "line_hint must be >= 1" in result
+    assert target.read_text() == "same\n"

tests/tools/test_image_generation_tool.py

@@ -138,6 +138,39 @@ async def test_generate_image_tool_reports_missing_aihubmix_key(tmp_path: Path)
     assert result.startswith("Error: AIHubMix API key is not configured")
 
 
+@pytest.mark.asyncio
+async def test_generate_image_tool_allows_ollama_without_api_key(
+    tmp_path: Path,
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    set_config_path(tmp_path / "config.json")
+    FakeImageClient.instances = []
+    monkeypatch.setattr(
+        "nanobot.agent.tools.image_generation.get_image_gen_provider",
+        lambda name: FakeImageClient if name == "ollama" else None,
+    )
+    tool = ImageGenerationTool(
+        workspace=tmp_path,
+        config=ImageGenerationToolConfig(
+            enabled=True,
+            provider="ollama",
+            model="x/z-image-turbo",
+        ),
+        provider_configs={"ollama": ProviderConfig(api_base="http://localhost:11434/v1")},
+    )
+
+    result = await tool.execute(prompt="draw a cat")
+
+    payload = json.loads(result)
+    assert len(payload["artifacts"]) == 1
+
+    fake = FakeImageClient.instances[0]
+    assert fake.kwargs["api_key"] is None
+    assert fake.kwargs["api_base"] == "http://localhost:11434/v1"
+    assert fake.calls[0]["aspect_ratio"] == "1:1"
+    assert fake.calls[0]["image_size"] == "1K"
+
+
 @pytest.mark.asyncio
 async def test_generate_image_tool_rejects_reference_outside_workspace(tmp_path: Path) -> None:
     set_config_path(tmp_path / "config.json")

tests/tools/test_notebook_tool.py

@@ -1,147 +0,0 @@
-"""Tests for NotebookEditTool — Jupyter .ipynb editing."""
-
-import json
-
-import pytest
-
-from nanobot.agent.tools.notebook import NotebookEditTool
-
-
-def _make_notebook(cells: list[dict] | None = None, nbformat: int = 4, nbformat_minor: int = 5) -> dict:
-    """Build a minimal valid .ipynb structure."""
-    return {
-        "nbformat": nbformat,
-        "nbformat_minor": nbformat_minor,
-        "metadata": {"kernelspec": {"display_name": "Python 3", "language": "python", "name": "python3"}},
-        "cells": cells or [],
-    }
-
-
-def _code_cell(source: str, cell_id: str | None = None) -> dict:
-    cell = {"cell_type": "code", "source": source, "metadata": {}, "outputs": [], "execution_count": None}
-    if cell_id:
-        cell["id"] = cell_id
-    return cell
-
-
-def _md_cell(source: str, cell_id: str | None = None) -> dict:
-    cell = {"cell_type": "markdown", "source": source, "metadata": {}}
-    if cell_id:
-        cell["id"] = cell_id
-    return cell
-
-
-def _write_nb(tmp_path, name: str, nb: dict) -> str:
-    p = tmp_path / name
-    p.write_text(json.dumps(nb), encoding="utf-8")
-    return str(p)
-
-
-class TestNotebookEdit:
-
-    @pytest.fixture()
-    def tool(self, tmp_path):
-        return NotebookEditTool(workspace=tmp_path)
-
-    @pytest.mark.asyncio
-    async def test_replace_cell_content(self, tool, tmp_path):
-        nb = _make_notebook([_code_cell("print('hello')"), _code_cell("x = 1")])
-        path = _write_nb(tmp_path, "test.ipynb", nb)
-        result = await tool.execute(path=path, cell_index=0, new_source="print('world')")
-        assert "Successfully" in result
-        saved = json.loads((tmp_path / "test.ipynb").read_text())
-        assert saved["cells"][0]["source"] == "print('world')"
-        assert saved["cells"][1]["source"] == "x = 1"
-
-    @pytest.mark.asyncio
-    async def test_insert_cell_after_target(self, tool, tmp_path):
-        nb = _make_notebook([_code_cell("cell 0"), _code_cell("cell 1")])
-        path = _write_nb(tmp_path, "test.ipynb", nb)
-        result = await tool.execute(path=path, cell_index=0, new_source="inserted", edit_mode="insert")
-        assert "Successfully" in result
-        saved = json.loads((tmp_path / "test.ipynb").read_text())
-        assert len(saved["cells"]) == 3
-        assert saved["cells"][0]["source"] == "cell 0"
-        assert saved["cells"][1]["source"] == "inserted"
-        assert saved["cells"][2]["source"] == "cell 1"
-
-    @pytest.mark.asyncio
-    async def test_delete_cell(self, tool, tmp_path):
-        nb = _make_notebook([_code_cell("A"), _code_cell("B"), _code_cell("C")])
-        path = _write_nb(tmp_path, "test.ipynb", nb)
-        result = await tool.execute(path=path, cell_index=1, edit_mode="delete")
-        assert "Successfully" in result
-        saved = json.loads((tmp_path / "test.ipynb").read_text())
-        assert len(saved["cells"]) == 2
-        assert saved["cells"][0]["source"] == "A"
-        assert saved["cells"][1]["source"] == "C"
-
-    @pytest.mark.asyncio
-    async def test_create_new_notebook_from_scratch(self, tool, tmp_path):
-        path = str(tmp_path / "new.ipynb")
-        result = await tool.execute(path=path, cell_index=0, new_source="# Hello", edit_mode="insert", cell_type="markdown")
-        assert "Successfully" in result or "created" in result.lower()
-        saved = json.loads((tmp_path / "new.ipynb").read_text())
-        assert saved["nbformat"] == 4
-        assert len(saved["cells"]) == 1
-        assert saved["cells"][0]["cell_type"] == "markdown"
-        assert saved["cells"][0]["source"] == "# Hello"
-
-    @pytest.mark.asyncio
-    async def test_invalid_cell_index_error(self, tool, tmp_path):
-        nb = _make_notebook([_code_cell("only cell")])
-        path = _write_nb(tmp_path, "test.ipynb", nb)
-        result = await tool.execute(path=path, cell_index=5, new_source="x")
-        assert "Error" in result
-
-    @pytest.mark.asyncio
-    async def test_non_ipynb_rejected(self, tool, tmp_path):
-        f = tmp_path / "script.py"
-        f.write_text("pass")
-        result = await tool.execute(path=str(f), cell_index=0, new_source="x")
-        assert "Error" in result
-        assert ".ipynb" in result
-
-    @pytest.mark.asyncio
-    async def test_preserves_metadata_and_outputs(self, tool, tmp_path):
-        cell = _code_cell("old")
-        cell["outputs"] = [{"output_type": "stream", "text": "hello\n"}]
-        cell["execution_count"] = 42
-        nb = _make_notebook([cell])
-        path = _write_nb(tmp_path, "test.ipynb", nb)
-        await tool.execute(path=path, cell_index=0, new_source="new")
-        saved = json.loads((tmp_path / "test.ipynb").read_text())
-        assert saved["metadata"]["kernelspec"]["language"] == "python"
-
-    @pytest.mark.asyncio
-    async def test_nbformat_45_generates_cell_id(self, tool, tmp_path):
-        nb = _make_notebook([], nbformat_minor=5)
-        path = _write_nb(tmp_path, "test.ipynb", nb)
-        await tool.execute(path=path, cell_index=0, new_source="x = 1", edit_mode="insert")
-        saved = json.loads((tmp_path / "test.ipynb").read_text())
-        assert "id" in saved["cells"][0]
-        assert len(saved["cells"][0]["id"]) > 0
-
-    @pytest.mark.asyncio
-    async def test_insert_with_cell_type_markdown(self, tool, tmp_path):
-        nb = _make_notebook([_code_cell("code")])
-        path = _write_nb(tmp_path, "test.ipynb", nb)
-        await tool.execute(path=path, cell_index=0, new_source="# Title", edit_mode="insert", cell_type="markdown")
-        saved = json.loads((tmp_path / "test.ipynb").read_text())
-        assert saved["cells"][1]["cell_type"] == "markdown"
-
-    @pytest.mark.asyncio
-    async def test_invalid_edit_mode_rejected(self, tool, tmp_path):
-        nb = _make_notebook([_code_cell("code")])
-        path = _write_nb(tmp_path, "test.ipynb", nb)
-        result = await tool.execute(path=path, cell_index=0, new_source="x", edit_mode="replcae")
-        assert "Error" in result
-        assert "edit_mode" in result
-
-    @pytest.mark.asyncio
-    async def test_invalid_cell_type_rejected(self, tool, tmp_path):
-        nb = _make_notebook([_code_cell("code")])
-        path = _write_nb(tmp_path, "test.ipynb", nb)
-        result = await tool.execute(path=path, cell_index=0, new_source="x", cell_type="raw")
-        assert "Error" in result
-        assert "cell_type" in result

tests/tools/test_search_tools.py

@@ -12,7 +12,7 @@ import pytest
 
 from nanobot.agent.loop import AgentLoop
 from nanobot.agent.subagent import SubagentManager, SubagentStatus
-from nanobot.agent.tools.search import GrepTool
+from nanobot.agent.tools.search import FindFilesTool, GrepTool
 from nanobot.agent.tools.web import WebSearchTool
 from nanobot.bus.queue import MessageBus
 from nanobot.config.schema import WebSearchConfig
@@ -33,6 +33,68 @@ async def test_web_search_tool_refreshes_dynamic_config_loader(monkeypatch) -> N
     assert await tool.execute("nanobot") == "duckduckgo:nanobot:3"
 
 
+@pytest.mark.asyncio
+async def test_find_files_filters_by_query_glob_and_type(tmp_path: Path) -> None:
+    (tmp_path / "src").mkdir()
+    (tmp_path / "src" / "settings_view.tsx").write_text("export {}\n", encoding="utf-8")
+    (tmp_path / "src" / "settings_api.py").write_text("pass\n", encoding="utf-8")
+    (tmp_path / "README.md").write_text("settings\n", encoding="utf-8")
+
+    tool = FindFilesTool(workspace=tmp_path, allowed_dir=tmp_path)
+    result = await tool.execute(
+        path=".",
+        query="settings",
+        glob="src/**",
+        type="ts",
+    )
+
+    assert result.splitlines() == ["src/settings_view.tsx"]
+
+
+@pytest.mark.asyncio
+async def test_find_files_can_include_directories(tmp_path: Path) -> None:
+    (tmp_path / "src" / "settings").mkdir(parents=True)
+    (tmp_path / "src" / "settings" / "index.ts").write_text("export {}\n", encoding="utf-8")
+
+    tool = FindFilesTool(workspace=tmp_path, allowed_dir=tmp_path)
+    result = await tool.execute(path="src", query="settings", include_dirs=True)
+
+    assert "src/settings/" in result.splitlines()
+    assert "src/settings/index.ts" in result.splitlines()
+
+
+@pytest.mark.asyncio
+async def test_find_files_supports_modified_sort_and_pagination(tmp_path: Path) -> None:
+    (tmp_path / "src").mkdir()
+    for idx, name in enumerate(("a.py", "b.py", "c.py"), start=1):
+        file_path = tmp_path / "src" / name
+        file_path.write_text("pass\n", encoding="utf-8")
+        os.utime(file_path, (idx, idx))
+
+    tool = FindFilesTool(workspace=tmp_path, allowed_dir=tmp_path)
+    result = await tool.execute(
+        path="src",
+        type="py",
+        sort="modified",
+        head_limit=1,
+        offset=1,
+    )
+
+    assert result.splitlines()[0] == "src/b.py"
+    assert "pagination: limit=1, offset=1" in result
+
+
+@pytest.mark.asyncio
+async def test_find_files_rejects_paths_outside_workspace(tmp_path: Path) -> None:
+    outside = tmp_path.parent / "outside-find-files.txt"
+    outside.write_text("secret\n", encoding="utf-8")
+
+    tool = FindFilesTool(workspace=tmp_path, allowed_dir=tmp_path)
+    result = await tool.execute(path=str(outside))
+
+    assert result.startswith("Error:")
+
+
 @pytest.mark.asyncio
 async def test_grep_respects_glob_filter_and_context(tmp_path: Path) -> None:
     (tmp_path / "src").mkdir()
@@ -249,6 +311,7 @@ def test_agent_loop_registers_grep(tmp_path: Path) -> None:
 
     loop = AgentLoop(bus=bus, provider=provider, workspace=tmp_path, model="test-model")
 
+    assert "find_files" in loop.tools.tool_names
     assert "grep" in loop.tools.tool_names
 
 
@@ -280,6 +343,7 @@ async def test_subagent_registers_grep(tmp_path: Path) -> None:
     status = SubagentStatus(task_id="sub-1", label="label", task_description="search task", started_at=time.monotonic())
     await mgr._run_subagent("sub-1", "search task", "label", {"channel": "cli", "chat_id": "direct"}, status)
 
+    assert "find_files" in captured["tool_names"]
     assert "grep" in captured["tool_names"]
 
 

tests/tools/test_tool_descriptions.py

@@ -0,0 +1,46 @@
+from nanobot.agent.tools.apply_patch import ApplyPatchTool
+from nanobot.agent.tools.exec_session import ListExecSessionsTool, WriteStdinTool
+from nanobot.agent.tools.filesystem import EditFileTool, ReadFileTool, WriteFileTool
+from nanobot.agent.tools.search import FindFilesTool, GrepTool
+from nanobot.agent.tools.shell import ExecTool
+
+
+def test_coding_tool_descriptions_steer_editing_priority() -> None:
+    apply_patch = ApplyPatchTool().description.lower()
+    edit_file = EditFileTool().description.lower()
+    write_file = WriteFileTool().description.lower()
+
+    assert "default tool for code edits" in apply_patch
+    assert "multi-file" in apply_patch
+    assert "dry_run=true" in apply_patch
+    assert "edit_file only for small exact replacements" in apply_patch
+
+    assert "small, exact replacement" in edit_file
+    assert "copied from read_file" in edit_file
+    assert "prefer apply_patch" in edit_file
+
+    assert "replace an entire file" in write_file
+    assert "prefer apply_patch" in write_file
+
+
+def test_coding_tool_descriptions_steer_discovery_and_shell_usage() -> None:
+    read_file = ReadFileTool().description.lower()
+    find_files = FindFilesTool().description.lower()
+    grep = GrepTool().description.lower()
+    exec_tool = ExecTool().description.lower()
+    write_stdin = WriteStdinTool().description.lower()
+    list_sessions = ListExecSessionsTool().description.lower()
+
+    assert "find_files/list_dir first" in read_file
+    assert "before editing" in read_file
+    assert "prefer it over shell find/ls" in find_files
+    assert "prefer this over shell grep" in grep
+
+    assert "tests, builds" in exec_tool
+    assert "prefer read_file/find_files/grep" in exec_tool
+    assert "apply_patch/write_file/edit_file" in exec_tool
+    assert "yield_time_ms" in exec_tool
+
+    assert "do not use this to start new commands" in write_stdin
+    assert "wait_for" in write_stdin
+    assert "recover a session_id" in list_sessions

tests/tools/test_tool_loader.py

@@ -89,9 +89,11 @@ def test_discover_finds_concrete_tools():
     loader = ToolLoader()
     discovered = loader.discover()
     class_names = {cls.__name__ for cls in discovered}
+    assert "ApplyPatchTool" in class_names
     assert "ExecTool" in class_names
     assert "MessageTool" in class_names
     assert "SpawnTool" in class_names
+    assert "WriteStdinTool" in class_names
 
 
 def test_discover_excludes_abstract_and_mcp():
@@ -406,7 +408,8 @@ def test_loader_registers_same_tools_as_old_hardcoded():
 
     expected = {
         "read_file", "write_file", "edit_file", "list_dir",
-        "grep", "notebook_edit", "exec", "web_search", "web_fetch",
+        "find_files", "grep", "exec", "write_stdin", "list_exec_sessions",
+        "web_search", "web_fetch",
         "message", "spawn", "cron",
     }
     actual = set(registered)

tests/tools/test_tool_validation.py

@@ -3,6 +3,8 @@ import subprocess
 import sys
 from typing import Any
 
+import pytest
+
 from nanobot.agent.tools import (
     ArraySchema,
     IntegerSchema,
@@ -15,6 +17,7 @@ from nanobot.agent.tools import (
 from nanobot.agent.tools.base import Tool
 from nanobot.agent.tools.registry import ToolRegistry
 from nanobot.agent.tools.shell import ExecTool
+from nanobot.security.network import configure_ssrf_whitelist
 
 
 class SampleTool(Tool):
@@ -218,6 +221,39 @@ def test_exec_extract_absolute_paths_ignores_relative_posix_segments() -> None:
     assert "/bin/python" not in paths
 
 
+def test_exec_extract_absolute_paths_ignores_urls() -> None:
+    cmd = 'curl -s -o /dev/null -w "%{http_code}" https://www.google.com'
+    paths = ExecTool._extract_absolute_paths(cmd)
+    assert paths == ["/dev/null"]
+
+
+@pytest.mark.parametrize(
+    "command",
+    [
+        'curl -s -o /dev/null -w "%{http_code}" https://www.google.com',
+        'wget -q -O - http://example.com 2>&1 | head -c 100',
+        'python3 -c "import urllib.request; print(urllib.request.urlopen(\'http://example.com\').read()[:100])"',
+    ],
+)
+def test_exec_guard_allows_public_urls(tmp_path, command: str) -> None:
+    tool = ExecTool(restrict_to_workspace=True)
+    error = tool._guard_command(command, str(tmp_path))
+    assert error is None
+
+
+def test_exec_guard_allows_whitelisted_internal_urls(tmp_path) -> None:
+    configure_ssrf_whitelist(["10.10.10.0/24"])
+    try:
+        tool = ExecTool(restrict_to_workspace=True)
+        error = tool._guard_command(
+            'curl -s -H "Authorization: Bearer ..." http://10.10.10.3:8123/api/',
+            str(tmp_path),
+        )
+        assert error is None
+    finally:
+        configure_ssrf_whitelist([])
+
+
 def test_exec_extract_absolute_paths_captures_posix_absolute_paths() -> None:
     cmd = "cat /tmp/data.txt > /tmp/out.txt"
     paths = ExecTool._extract_absolute_paths(cmd)

tests/utils/test_file_edit_events.py

@@ -5,12 +5,13 @@ from pathlib import Path
 from types import SimpleNamespace
 
 from nanobot.utils.file_edit_events import (
+    StreamingFileEditTracker,
     build_file_edit_end_event,
     build_file_edit_start_event,
     line_diff_stats,
     prepare_file_edit_tracker,
+    prepare_file_edit_trackers,
     read_file_snapshot,
-    StreamingFileEditTracker,
 )
 
 
@@ -81,6 +82,63 @@ def test_binary_file_is_reported_but_not_counted(tmp_path: Path) -> None:
     assert (event["added"], event["deleted"]) == (0, 0)
 
 
+def test_apply_patch_prepares_trackers_for_each_touched_file(tmp_path: Path) -> None:
+    (tmp_path / "src").mkdir()
+    existing = tmp_path / "src" / "existing.py"
+    existing.write_text("old\nkeep\n", encoding="utf-8")
+    delete_me = tmp_path / "src" / "delete_me.py"
+    delete_me.write_text("gone\n", encoding="utf-8")
+
+    edits = [
+        {"path": "src/new.py", "action": "add", "new_text": "fresh"},
+        {"path": "src/existing.py", "action": "replace", "old_text": "old", "new_text": "new"},
+        {"path": "src/delete_me.py", "action": "delete", "old_text": "gone\n"},
+    ]
+
+    trackers = prepare_file_edit_trackers(
+        call_id="call-patch",
+        tool_name="apply_patch",
+        tool=None,
+        workspace=tmp_path,
+        params={"edits": edits},
+    )
+
+    assert [tracker.display_path for tracker in trackers] == [
+        "src/new.py",
+        "src/existing.py",
+        "src/delete_me.py",
+    ]
+
+    (tmp_path / "src" / "new.py").write_text("fresh\n", encoding="utf-8")
+    existing.write_text("new\nkeep\n", encoding="utf-8")
+    delete_me.unlink()
+
+    events = [build_file_edit_end_event(tracker, {"edits": edits}) for tracker in trackers]
+    by_path = {event["path"]: event for event in events}
+    assert (by_path["src/new.py"]["added"], by_path["src/new.py"]["deleted"]) == (1, 0)
+    assert (by_path["src/existing.py"]["added"], by_path["src/existing.py"]["deleted"]) == (1, 1)
+    assert (by_path["src/delete_me.py"]["added"], by_path["src/delete_me.py"]["deleted"]) == (0, 1)
+
+
+def test_apply_patch_dry_run_does_not_prepare_file_edit_trackers(tmp_path: Path) -> None:
+    (tmp_path / "file.txt").write_text("old\n", encoding="utf-8")
+
+    trackers = prepare_file_edit_trackers(
+        call_id="call-patch",
+        tool_name="apply_patch",
+        tool=None,
+        workspace=tmp_path,
+        params={
+            "dry_run": True,
+            "edits": [
+                {"path": "file.txt", "action": "replace", "old_text": "old", "new_text": "new"}
+            ],
+        },
+    )
+
+    assert trackers == []
+
+
 def test_oversized_write_file_end_uses_known_content_for_exact_count(tmp_path: Path) -> None:
     target = tmp_path / "large.txt"
     params = {"path": "large.txt", "content": "x" * (2 * 1024 * 1024 + 1)}
@@ -140,6 +198,58 @@ def test_streaming_write_file_tracker_emits_live_line_counts(tmp_path: Path) ->
     assert events[-1]["deleted"] == 0
 
 
+def test_streaming_apply_patch_tracker_emits_live_counts_per_file(tmp_path: Path) -> None:
+    (tmp_path / "src").mkdir()
+    (tmp_path / "src" / "existing.py").write_text("old\nkeep\n", encoding="utf-8")
+    events: list[dict] = []
+
+    async def emit(batch: list[dict]) -> None:
+        events.extend(batch)
+
+    async def run() -> None:
+        tracker = StreamingFileEditTracker(workspace=tmp_path, tools={}, emit=emit)
+        await tracker.update({
+            "index": 0,
+            "call_id": "call-patch",
+            "name": "apply_patch",
+            "arguments_delta": (
+                '{"edits":[{"path":"src/existing.py","action":"replace","old_text":"old","new_text":"new"}'
+                ',{"path":"src/new.py","action":"add","new_text":"fresh"}]}'
+            ),
+        })
+
+    asyncio.run(run())
+
+    by_path = {event["path"]: event for event in events}
+    assert by_path["src/existing.py"]["tool"] == "apply_patch"
+    assert by_path["src/existing.py"]["status"] == "editing"
+    assert by_path["src/existing.py"]["approximate"] is True
+    assert (by_path["src/existing.py"]["added"], by_path["src/existing.py"]["deleted"]) == (1, 1)
+    assert (by_path["src/new.py"]["added"], by_path["src/new.py"]["deleted"]) == (1, 0)
+
+
+def test_streaming_apply_patch_tracker_skips_dry_run(tmp_path: Path) -> None:
+    events: list[dict] = []
+
+    async def emit(batch: list[dict]) -> None:
+        events.extend(batch)
+
+    async def run() -> None:
+        tracker = StreamingFileEditTracker(workspace=tmp_path, tools={}, emit=emit)
+        await tracker.update({
+            "index": 0,
+            "call_id": "call-patch",
+            "name": "apply_patch",
+            "arguments_delta": (
+                '{"dry_run":true,"edits":[{"path":"dry.md","action":"add","new_text":"preview"}]}'
+            ),
+        })
+
+    asyncio.run(run())
+
+    assert events == []
+
+
 def test_streaming_write_file_tracker_emits_pending_before_path(tmp_path: Path) -> None:
     events: list[dict] = []
 
@@ -308,6 +418,43 @@ def test_streaming_tracker_applies_canonical_call_id_to_final_tool(tmp_path: Pat
     asyncio.run(run())
 
 
+def test_streaming_tracker_does_not_restore_duplicate_canonical_ids(tmp_path: Path) -> None:
+    events: list[dict] = []
+
+    async def emit(batch: list[dict]) -> None:
+        events.extend(batch)
+
+    async def run() -> None:
+        tracker = StreamingFileEditTracker(workspace=tmp_path, tools={}, emit=emit)
+        await tracker.update({
+            "index": 0,
+            "call_id": "call_dup",
+            "name": "write_file",
+            "arguments_delta": '{"path":"a.md","content":"one\\n"}',
+        })
+        await tracker.update({
+            "index": 1,
+            "call_id": "call_dup",
+            "name": "write_file",
+            "arguments_delta": '{"path":"b.md","content":"two\\n"}',
+        })
+        final_a = SimpleNamespace(
+            id="call_dup",
+            name="write_file",
+            arguments={"path": "a.md", "content": "one\n"},
+        )
+        final_b = SimpleNamespace(
+            id="call_unique",
+            name="write_file",
+            arguments={"path": "b.md", "content": "two\n"},
+        )
+        tracker.apply_final_call_ids([final_a, final_b])
+        assert final_a.id == "call_dup"
+        assert final_b.id == "call_unique"
+
+    asyncio.run(run())
+
+
 def test_streaming_edit_file_tracker_flushes_small_pending_count(tmp_path: Path) -> None:
     target = tmp_path / "small.py"
     target.write_text("old\n", encoding="utf-8")