lcode-cli 0.26.0__py3-none-any.whl → 0.27.0__py3-none-any.whl

lcode/__init__.py

@@ -3,7 +3,7 @@
 From a program: `from lcode import Session` (see lcode.api).
 """
 
-__version__ = "0.26.0"
+__version__ = "0.27.0"
 
 API = ("Session", "Result", "Options", "SetupError")
 

lcode/agent.py

@@ -234,6 +234,7 @@ class Settings:
     notify_after: int = 30  # seconds: a request this long notifies when it's done or waits for an answer
     max_parallel_agents: int = 1
     secret_check: bool = True  # scan what git commit and git push would add (lcode.secretscan)
+    compact_at: int = 0  # tokens: make room at this size even when the window is larger (0: only at 85%)
     repeat_limit: int = 3  # identical calls with identical results before the model is told (lcode.repeats)
 
 
@@ -270,6 +271,7 @@ class Agent:
         self.agent_runs: list[subagents.Record] = []  # subagents run in this session, for /agents
         self.plan = ""  # the plan the user approved; kept through compaction
         self.pruned = self.compacted = 0  # how often the context was pruned or summarized automatically
+        self.summarized_size = 0  # tokens right after the last summary (0: none in this conversation)
         self._extensions: tuple[Path, extensions.Extensions] | None = None
         self.skills_loaded: set[str] = set()  # skills whose instructions are in the conversation
         # Set on subagents (see lcode.subagents):
@@ -514,6 +516,7 @@ class Agent:
         return WEB_PROMPT.format(tools=tools, date=dt.date.today().isoformat())
 
     def reset(self) -> None:
+        self.summarized_size = 0
         self.messages = [{"role": "system", "content": self.system_prompt()}]
         self._mcp_prompt = ""
         self.tools.read_mtimes.clear()
@@ -1046,13 +1049,27 @@ class Agent:
         return text + ("\n\n" + "\n\n".join(attached) if attached else "")
 
     # -- context management
+    def compact_limit(self) -> int:
+        """The tokens in use at which lcode makes room: 85% of the window, or `compact_at` when that's lower.
+        Small models lose track in long contexts well before a large window is full."""
+        limit = int(AUTO_COMPACT_RATIO * self.settings.context)
+        if self.settings.compact_at > 0:
+            limit = min(limit, self.settings.compact_at)
+        return limit
+
     def maybe_compact(self) -> None:
-        if self.ctx_used <= AUTO_COMPACT_RATIO * self.settings.context:
+        limit = self.compact_limit()
+        if self.ctx_used <= limit:
             return
+        enough = int(limit * PRUNED_ENOUGH / AUTO_COMPACT_RATIO)  # after pruning, a summary isn't needed below this
         if self.settings.prune:
-            saved = context_tools.prune(self.messages)  # tool output from before the last two requests
-            if self.ctx_used - saved // 3 > PRUNED_ENOUGH * self.settings.context:
-                saved += context_tools.prune(self.messages, keep=1)  # not enough: before the last request
+            removed: list[str] = []  # files and pages whose only copy goes
+            saved = context_tools.prune(self.messages, removed=removed)  # tool output from before the last two requests
+            if self.ctx_used - saved // 3 > enough:
+                saved += context_tools.prune(
+                    self.messages, keep=1, removed=removed
+                )  # not enough: before the last request
+            context_tools.note_removed(self.messages, removed)
             if saved:
                 self.pruned += 1
                 self.ctx_used = max(len(self.messages[0]["content"]) // 3, self.ctx_used - saved // 3)
@@ -1060,9 +1077,17 @@ class Agent:
                     f"[dim]Removed old tool output from the conversation (~{format_tokens(saved // 3)} tokens) to "
                     "make room.[/]"
                 )
-                if self.ctx_used <= PRUNED_ENOUGH * self.settings.context:
+                if self.ctx_used <= enough:
                     return
-        self.console.print("[yellow]Context is nearly full — compacting the conversation…[/]")
+        window_full = self.ctx_used > AUTO_COMPACT_RATIO * self.settings.context
+        if not window_full and self.summarized_size and self.ctx_used - self.summarized_size < limit // 4:
+            return  # summarized not long ago: summarizing again so soon would only lose more
+        if limit < AUTO_COMPACT_RATIO * self.settings.context:
+            self.console.print(
+                f"[yellow]The conversation reached {format_tokens(limit)} tokens (compact_at) — summarizing it…[/]"
+            )
+        else:
+            self.console.print("[yellow]Context is nearly full — compacting the conversation…[/]")
         self.compacted += 1
         self.compact()
 
@@ -1083,9 +1108,13 @@ class Agent:
         with self.console.status("[cyan]Compacting…[/]"):
             for chunk in self.chat([*self.messages, {"role": "user", "content": instructions}], None, False):
                 summary += chunk.get("message", {}).get("content", "")
+        requests = context_tools.user_requests(self.messages)
         self.messages = [
             {"role": "system", "content": self.system_prompt()},
-            {"role": "user", "content": f"[Summary of our conversation so far]\n\n{summary}"},
+            {
+                "role": "user",
+                "content": f"{sessions.SUMMARY_PREFIX}\n\n{summary}" + context_tools.requests_block(requests),
+            },
             {"role": "assistant", "content": "Got it — I have the context from the summary and will continue."},
         ]
         if self.plan:  # the approved plan stays word for word
@@ -1097,6 +1126,7 @@ class Agent:
             )
             self.skills_loaded.clear()
         self.ctx_used = sum(len(m["content"]) for m in self.messages) // 3
+        self.summarized_size = self.ctx_used
         self.reflected = len(self.messages)
         self.console.print(Panel(Markdown(summary), title="Compacted summary", border_style="blue"))
 

lcode/api.py

@@ -196,6 +196,7 @@ def open_agent(cwd: Path, options: Options, console: Console, hw: Hardware | Non
         notify_after=cfg["notify_after"],
         secret_check=cfg["secret_check"],
         repeat_limit=cfg["repeat_limit"],
+        compact_at=cfg["compact_at"],
     )
     agent = Agent(ollama, settings, cwd, console=console)
     agent.interactive = options.interactive

lcode/cli.py

@@ -579,6 +579,7 @@ def cmd_bench(args) -> None:
             web="off",
             checkpoints=False,
             prune=not args.no_prune,
+            compact_at=cfg["compact_at"] if args.compact_at is None else args.compact_at,
             repo_map=args.repo_map,
             embed_model=cfg["embed_model"] if args.code_search else "off",
         )
@@ -678,6 +679,14 @@ def cmd_chat(args) -> None:
         sys.exit(exit_code)
 
 
+def compact_tokens(value: str) -> int:
+    """`--compact-at`: a token count such as 64k, or 0."""
+    try:
+        return config.parse_compact_at(value)
+    except ConfigError as e:
+        raise argparse.ArgumentTypeError(str(e)) from e
+
+
 def build_parser() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(
         prog="lcode",
@@ -765,6 +774,12 @@ def build_subparsers() -> dict[str, argparse.ArgumentParser]:
     p.add_argument("--repo-map", action="store_true", help="give the model the repository map (off by default)")
     p.add_argument("--code-search", action="store_true", help="index each task's folder and offer semantic code search")
     p.add_argument("--no-prune", action="store_true", help="don't remove old tool output (to compare, with --session)")
+    p.add_argument(
+        "--compact-at",
+        type=compact_tokens,
+        metavar="TOKENS",
+        help="summarize at this many tokens, e.g. 64k (default: the compact_at setting; 0: only at 85%%)",
+    )
     subs["bench"] = p
     p = argparse.ArgumentParser(
         prog="lcode index",

lcode/config.py

@@ -61,6 +61,7 @@ SETTINGS: dict[str, tuple[object, type, str]] = {
     "notify_after": (30, int, "seconds a request runs before it notifies (with notify on)"),
     "repeat_limit": (3, int, "identical tool calls with identical results before lcode steps in (0: never)"),
     "secret_check": (True, bool, "before git commit and git push, look for passwords, keys and tokens they'd add"),
+    "compact_at": (65536, int, "summarize at this many tokens even when the window is larger (0: only at 85%)"),
     "max_parallel_agents": (1, int, "subagents that may run at the same time (more needs OLLAMA_NUM_PARALLEL)"),
 }
 ENV_OVERRIDES = {
@@ -81,6 +82,19 @@ class ConfigError(ValueError):
     pass
 
 
+MIN_COMPACT_AT = 16384  # below this, the system prompt and a summary alone come close to the ceiling
+
+
+def parse_compact_at(value: str | int) -> int:
+    """compact_at: a token count like parse_context's, at least 16K, or 0 (off)."""
+    if str(value).strip().lower() in ("0", "off", "false", "none"):
+        return 0
+    tokens = parse_context(value)
+    if tokens < MIN_COMPACT_AT:
+        raise ConfigError(f"compact_at {tokens} is too small: use at least 16k, or 0 to turn it off")
+    return tokens
+
+
 def parse_context(value: str | int) -> int:
     """Parse '131072', '128k', '128K' or '1m' into a token count (k = 1024)."""
     if isinstance(value, int):
@@ -118,6 +132,8 @@ def coerce(key: str, value: object) -> object:
     _, typ, _ = SETTINGS[key]
     if key == "context":
         return parse_context(value)  # type: ignore[arg-type]
+    if key == "compact_at":
+        return parse_compact_at(value)  # type: ignore[arg-type]
     if key in ("ollama_host", "searxng_url"):
         return normalize_host(str(value))
     if key == "base_url":

lcode/context.py

@@ -29,6 +29,10 @@ if TYPE_CHECKING:
 KEEP_RECENT_REQUESTS = 2  # tool results of the last requests stay as they are
 MIN_PRUNE_CHARS = 400  # shorter results aren't worth replacing
 PRUNED = "[lcode: "  # how stubs start, so they're never pruned twice
+GONE = (  # a removed file read: firm, because models answer from the stub instead of reading it again
+    "earlier; its content was removed to save context and isn't in this conversation any more. Read it again "
+    "before answering anything about it.]"
+)
 KEEP_TOOLS = {"agent", "skill", "memory", "todo_write", "present_plan"}  # short, or still guiding the work
 ERROR_LINE = re.compile(
     r"error|exception|traceback|failed|failure|fatal|panic|assert|denied|not found|cannot|can't|undefined", re.I
@@ -37,6 +41,56 @@ MAX_ERROR_LINES = 40
 OUTPUT_DAYS = 7  # saved full outputs are deleted after this
 
 
+# ----------------------------------------------------------------------------- the user's requests
+
+REQUESTS_HEADER = "[The user's requests in this conversation, word for word, oldest first]"
+MAX_REQUESTS = 8  # the most recent ones are kept through a summary
+MAX_REQUEST_CHARS = 1500
+# What lcode appends to the user's words: attached files, images and folders, and its own notes.
+ATTACHED = re.compile(r"\n\n(?:<file path=|<image path=|<directory path=|\[lcode[:\]] |\[The user wants the )")
+
+
+def request_text(content: str) -> str:
+    """The user's own words in a message, without what lcode attached to it."""
+    cut = ATTACHED.search(content)
+    return (content[: cut.start()] if cut else content).strip()
+
+
+def user_requests(messages: list[dict]) -> list[str]:
+    """What the user asked in the conversation, oldest first, including the requests an earlier summary kept."""
+    requests: list[str] = []
+    for message in messages:
+        content = message.get("content") or ""
+        if message.get("role") != "user":
+            continue
+        if content.startswith(SUMMARY_PREFIX):
+            start = content.find(REQUESTS_HEADER)
+            if start >= 0:
+                rest = content[start + len(REQUESTS_HEADER) :]
+                try:
+                    kept, _ = json.JSONDecoder().raw_decode(rest[rest.index("[") :])
+                    requests += [str(r) for r in kept]
+                except ValueError:
+                    pass
+            continue
+        if content.startswith("[lcode]"):
+            continue  # lcode's own nudges
+        text = request_text(content)
+        if text:
+            requests.append(text)
+    return requests
+
+
+def requests_block(requests: list[str]) -> str:
+    """The user's latest requests, word for word, to keep the goal through a summary."""
+    if not requests:
+        return ""
+    kept = [r if len(r) <= MAX_REQUEST_CHARS else f"{r[: MAX_REQUEST_CHARS - 200]} […] {r[-150:]}" for r in requests]
+    older = len(kept) - MAX_REQUESTS
+    note = f" (and {older} earlier, in the summary)" if older > 0 else ""
+    return f"\n\n{REQUESTS_HEADER}{note}\n{json.dumps(kept[-MAX_REQUESTS:], ensure_ascii=False, indent=1)}"
+
+
 # ----------------------------------------------------------------------------- pruning
 
 
@@ -63,7 +117,7 @@ def stub(name: str, args: dict, content: str) -> str:
         if args.get("offset") or args.get("limit"):
             start = int(args.get("offset") or 1)
             span = f" from line {start}"
-        return f"{PRUNED}read {args.get('path', 'a file')}{span} earlier; removed to save context. Read it again if you need it.]"
+        return f"{PRUNED}read {args.get('path', 'a file')}{span} {GONE}"
     if name == "bash":
         command = " ".join(str(args.get("command", "")).split())
         command = command if len(command) <= 80 else command[:79] + "…"
@@ -92,8 +146,9 @@ def boundary(messages: list[dict], keep: int = KEEP_RECENT_REQUESTS) -> int:
     return requests[-keep] if len(requests) >= keep else 0
 
 
-def prune(messages: list[dict], keep: int = KEEP_RECENT_REQUESTS) -> int:
-    """Replace stale tool results with stubs, in place. Returns the number of characters saved."""
+def prune(messages: list[dict], keep: int = KEEP_RECENT_REQUESTS, removed: list[str] | None = None) -> int:
+    """Replace stale tool results with stubs, in place. Returns the number of characters saved; the files and
+    pages whose only copy went are added to `removed`."""
     calls = calls_for_results(messages)
     edge = boundary(messages, keep)
     # A read is superseded by a later read of the whole file, or of the same lines: not by a later
@@ -118,12 +173,34 @@ def prune(messages: list[dict], keep: int = KEEP_RECENT_REQUESTS) -> int:
             continue
         new = stub(name, args, content)
         if reread:
-            new = new.replace("earlier; removed", "earlier (read again later); removed")
+            new = new.replace(
+                GONE, "earlier (read again later); removed to save context. Read it again if you need it.]"
+            )
+        elif removed is not None and name in ("read_file", "web_fetch"):
+            what = str(args.get("path") or args.get("url") or "")
+            if what and what not in removed:
+                removed.append(what)
         messages[i]["content"] = new
         saved += len(content) - len(new)
     return saved
 
 
+def note_removed(messages: list[dict], removed: list[str]) -> None:
+    """Tell the model, next to the request it's working on, which files it no longer has: a stub deep in the
+    conversation is easy to overlook, and models then answer from memory instead of reading again."""
+    if not removed:
+        return
+    for message in reversed(messages):
+        content = str(message.get("content", ""))
+        if message.get("role") == "user" and not content.startswith(("[lcode]", SUMMARY_PREFIX)):
+            names = ", ".join(removed[:10]) + (f" and {len(removed) - 10} more" if len(removed) > 10 else "")
+            message["content"] = (
+                f"{content}\n\n[lcode] To make room, lcode removed what you read earlier from: {names}. It isn't in "
+                "this conversation any more: read it again before answering anything about it, don't answer from memory."
+            )
+            return
+
+
 # ----------------------------------------------------------------------------- long output
 
 

lcode/repl.py

@@ -242,7 +242,8 @@ def context_command(agent: Agent, arg: str, hardware: Hardware) -> None:
     c.print(
         f"In use: {format_tokens(agent.ctx_used)} of {format_tokens(s.context)} tokens "
         f"({100 * agent.ctx_used / s.context:.0f}%) in {len(agent.messages)} message"
-        f"{'' if len(agent.messages) == 1 else 's'}; auto-compacts at 85%."
+        f"{'' if len(agent.messages) == 1 else 's'}; makes room at {format_tokens(agent.compact_limit())} "
+        + ("(compact_at)." if agent.compact_limit() < AUTO_COMPACT_RATIO * s.context else "(85%).")
     )
     if agent.mcp and agent.mcp.ready():
         how = "found on demand" if agent.mcp.searching(s.context) else "sent with every request"

{lcode_cli-0.26.0.dist-info → lcode_cli-0.27.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: lcode-cli
-Version: 0.26.0
+Version: 0.27.0
 Summary: A local-first terminal coding agent powered by open-weight models on your own GPU or Mac, via Ollama.
 Project-URL: Homepage, https://nasser1941.github.io/lcode/
 Project-URL: Documentation, https://nasser1941.github.io/lcode/

{lcode_cli-0.26.0.dist-info → lcode_cli-0.27.0.dist-info}/RECORD

@@ -1,20 +1,20 @@
-lcode/__init__.py,sha256=xjCrbnr5jMJNipwGklkGM9ZGwF83DFfVEQPHFTwk3IY,473
+lcode/__init__.py,sha256=JUcNjfBPUQX6hKCFSklgC04DhC6xrDnysFFhCU7p5Xc,473
 lcode/__main__.py,sha256=s5N5pryX2FAu93GGZ3FxUrIXHWGzxz66lKUoaV_h8Ws,35
 lcode/acp.py,sha256=Tpc8lsvffZSYbTRI4t7X4E2chahqZIPcKeYIcL5bV3Y,29035
 lcode/action.py,sha256=wuT5F9EJCdEligPeytzmEi8FpahWBhXer528tpuTj_k,16711
-lcode/agent.py,sha256=kAjvCq2XrXqNVyrwbgLhG0XOtXdY0TVk-ty2Oou6hnk,56297
-lcode/api.py,sha256=i6mxPCkD1ObrVQQeJ7LacEtsjuhQFdV21fM9FTj3hrg,15418
+lcode/agent.py,sha256=tGNjbs8cw2X7IUBb70juI3JH5IpXmmIXOcteTsMhOtA,57936
+lcode/api.py,sha256=aqWnGCy1jNuIktJEHo9ncbHNTXn2QO3BoNiggyo9ZmQ,15456
 lcode/backends.py,sha256=dtJHrC6ys73bRDg64z0tQz1PavmeAkiODZu1fOO9ExQ,20635
 lcode/bench.py,sha256=7ICipu_2GXW6vE519XeZucc2GSWA44votT8JvqcNv1k,40964
 lcode/bench_backend.py,sha256=X2fo-zRX92Xp3KMxSsFlWioc2vRupBTtowj5kLME8mw,14287
 lcode/bench_runtime.py,sha256=EjzNgIvUkdbT8cbSy1TpmlyeIk6e-ipjlDFpM7Dnqx0,6835
 lcode/catalog.py,sha256=pZ1azX9OH2r4JE2c6E5OfwywpgS39-W2oXzoCHJhmtM,4141
 lcode/checkpoints.py,sha256=eqPtmPe44-aweWqc2H21ROogwzIt3NpvcUobsaCHoGY,18354
-lcode/cli.py,sha256=cH5mcYi54Aofcv0PDNgFmFFQX8OQjhwTGdbWMUM_FG8,40289
+lcode/cli.py,sha256=M6Mjd5BROSGlZj4J6TrSZMJqI-OVfUEWPoC0TQyOQ28,40831
 lcode/clipboard.py,sha256=nTSdJyCXPdtjH947RjvB3QvRqnL5HZsS9KB8EkC42cc,5138
 lcode/codesearch.py,sha256=Io8leN1nb_Y-Dvlm9xaGtwUWYXX-ooswuznJV6dGU1s,10766
-lcode/config.py,sha256=g7oT5ElKonmbR7_4itgJllTp81wGEYZy1fRZJnAvzOw,10481
-lcode/context.py,sha256=qJymLE3eYeaF6qVOzlUwDURqlky__8cskl_6vXeU3AA,10701
+lcode/config.py,sha256=q1zGzH3p5U23ai6O9Jai3dS-s30CuQ9gc5cWX0_yxWE,11195
+lcode/context.py,sha256=_f0NbXyjA4SyH2RCr49AiWwtAfr_PVDaqyFQ5fZDhkg,14404
 lcode/extensions.py,sha256=W0HFDl0BvROzr7i_qtabHdIbacBgP5o5qIJLzoM2oNE,16806
 lcode/frontmatter.py,sha256=Bx0n4vLPhp7ZCWx-g7xqzqNy5VoKBxyeeikh5UFB_gA,2441
 lcode/gitflow.py,sha256=6j_nnCBZXkX1qhTI7K4CyZ5D0NAZLpH96weFEo64AkQ,27913
@@ -31,7 +31,7 @@ lcode/permissions.py,sha256=i04YLtqYCxwApgawomPp4d35uk9HAJtpKY__gfw8j9s,6347
 lcode/planning.py,sha256=Q2upaoZPnXDMQT2F-ETxX1lk_wDntTzhSKNVYIQSoQA,6540
 lcode/render.py,sha256=gMvf4W3qkLUJ4Vot3az_hP_zRDAItJC9pP-68dHFkfA,1375
 lcode/repeats.py,sha256=uzyAewX03nJf5dKwYFH4y9ZDnh0Lvy2k0qC2vdntM5Y,4061
-lcode/repl.py,sha256=ZKd4l4wDGKHVaGz8bxjLGc2gRc2W-RpHPQYG9M2A_Zw,49441
+lcode/repl.py,sha256=Y53tTvdoTP6CZOtq96CzbvPcwVlYNc9fppMV0hAlRSY,49573
 lcode/repomap.py,sha256=1GRJgEUjBl9XHSXsF7tSGXBCEgsY-3CzwMohaTudZ_M,13969
 lcode/sandbox.py,sha256=u_pkrVRXhCGhh-wFDPwuZ3jGG7UeXxXRAeBNsm37ZvE,8608
 lcode/secretscan.py,sha256=6Euvfk2gCtK7lZbuQD84zgWuSECi6OnSw8V5rFu1tfU,13575
@@ -57,8 +57,8 @@ lcode/servers/__init__.py,sha256=qrIhxEodEB8cjKEQ4Cicc0GsQhE2OH-9qlVHzr3-tq8,77
 lcode/servers/encord.py,sha256=WSauawL1UKYZCUAG1oalcKL_An3DVof-JM6xIgFyQSE,12769
 lcode/servers/valohai.py,sha256=e5xZGIoa4cja4f5i85q1GpL9c7cglUjV8jN2co1CFMY,14430
 lcode/servers/xai.py,sha256=h2emAvHSnkuB9WmJInlynsDhvxJwNVD2AHFX7vqMXNc,13627
-lcode_cli-0.26.0.dist-info/METADATA,sha256=iHy2mJa4Bk0LVY3hiDAkHxhBs2uqk21--IGY27MaePw,12620
-lcode_cli-0.26.0.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
-lcode_cli-0.26.0.dist-info/entry_points.txt,sha256=Hxsn_itbnbgft3U0FwxWdmEt0yoAV2LB-nJDnL9WT20,172
-lcode_cli-0.26.0.dist-info/licenses/LICENSE,sha256=JWjmoL7nNIC1XUa-dZm2hwLUgjUQMFo6k8APb0idNzs,1074
-lcode_cli-0.26.0.dist-info/RECORD,,
+lcode_cli-0.27.0.dist-info/METADATA,sha256=pASpYtQ_MeN-50aD2sdpTfxMKuX2Tz00LaJa2pT1DmM,12620
+lcode_cli-0.27.0.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
+lcode_cli-0.27.0.dist-info/entry_points.txt,sha256=Hxsn_itbnbgft3U0FwxWdmEt0yoAV2LB-nJDnL9WT20,172
+lcode_cli-0.27.0.dist-info/licenses/LICENSE,sha256=JWjmoL7nNIC1XUa-dZm2hwLUgjUQMFo6k8APb0idNzs,1074
+lcode_cli-0.27.0.dist-info/RECORD,,