大規模履歴向けread_messages pagination対応

1 files changed, 273 insertions, 25 deletions

diff --git a/src/mcp/tools/read_messages.c b/src/mcp/tools/read_messages.c
index 5a9e49f..1581534 100644
--- a/src/mcp/tools/read_messages.c
+++ b/src/mcp/tools/read_messages.c
@@ -3,25 +3,186 @@
 #include "mcp/tools/common/common.h"
 #include "mcp/tools/common/context.h"
 
+#include <stdint.h>
 #include <stdlib.h>
 #include <string.h>
 
 #include "base/allocator.h"
+#include "storage/codec.h"
+
+#define READ_DEFAULT_LIMIT 100
+#define READ_MAX_LIMIT 1000
+#define READ_RESPONSE_BUDGET (8U * 1024U * 1024U - 64U * 1024U)
+#define CURSOR_BYTES 47U
+#define CURSOR_TEXT_MAX 64U
+
+typedef struct history_cursor
+{
+  int64_t timestamp;
+  char message_id[27];
+} history_cursor_t;
+
+static uint64_t
+session_hash(const char *value)
+{
+  uint64_t hash = UINT64_C(1469598103934665603);
+  while (*value)
+    {
+      hash ^= (unsigned char)*value++;
+      hash *= UINT64_C(1099511628211);
+    }
+  return hash;
+}
+
+static size_t
+base64url_encode(const unsigned char *input, size_t length, char *output, size_t capacity)
+{
+  static const char alphabet[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_";
+  size_t source = 0, target = 0;
+  while (source < length)
+    {
+      uint32_t value = (uint32_t)input[source++] << 16;
+      unsigned available = 1;
+      if (source < length)
+        {
+          value |= (uint32_t)input[source++] << 8;
+          available++;
+        }
+      if (source < length)
+        {
+          value |= input[source++];
+          available++;
+        }
+      if (target + available + 1 >= capacity)
+        {
+          return 0;
+        }
+      output[target++] = alphabet[(value >> 18) & 63];
+      output[target++] = alphabet[(value >> 12) & 63];
+      if (available > 1)
+        {
+          output[target++] = alphabet[(value >> 6) & 63];
+        }
+      if (available > 2)
+        {
+          output[target++] = alphabet[value & 63];
+        }
+    }
+  output[target] = '\0';
+  return target;
+}
 
 static int
-compare_history(const void *left, const void *right)
+base64_value(unsigned char value)
+{
+  if (value >= 'A' && value <= 'Z')
+    {
+      return value - 'A';
+    }
+  if (value >= 'a' && value <= 'z')
+    {
+      return value - 'a' + 26;
+    }
+  if (value >= '0' && value <= '9')
+    {
+      return value - '0' + 52;
+    }
+  if (value == '-')
+    {
+      return 62;
+    }
+  if (value == '_')
+    {
+      return 63;
+    }
+  return -1;
+}
+
+static bool
+base64url_decode(const char *input, unsigned char output[CURSOR_BYTES])
 {
-  const tiny_store_entry_t *a = *(const tiny_store_entry_t *const *)left;
-  const tiny_store_entry_t *b = *(const tiny_store_entry_t *const *)right;
-  if (a->message.timestamp_ms < b->message.timestamp_ms)
+  size_t length = strlen(input), source = 0, target = 0;
+  uint32_t accumulator = 0;
+  unsigned bits = 0;
+  if (length != 63)
+    {
+      return false;
+    }
+  while (source < length)
+    {
+      int value = base64_value((unsigned char)input[source++]);
+      if (value < 0)
+        {
+          return false;
+        }
+      accumulator = (accumulator << 6) | (uint32_t)value;
+      bits += 6;
+      if (bits >= 8)
+        {
+          bits -= 8;
+          if (target >= CURSOR_BYTES)
+            {
+              return false;
+            }
+          output[target++] = (unsigned char)(accumulator >> bits);
+          accumulator &= bits ? (UINT32_C(1) << bits) - 1 : 0;
+        }
+    }
+  return target == CURSOR_BYTES && accumulator == 0;
+}
+
+static bool
+cursor_encode(const char *session, const tiny_message_t *message, char output[CURSOR_TEXT_MAX])
+{
+  unsigned char data[CURSOR_BYTES] = { 0 };
+  data[0] = 1;
+  tiny_codec_put_u64(data + 1, session_hash(session));
+  tiny_codec_put_u64(data + 9, (uint64_t)message->timestamp_ms);
+  memcpy(data + 17, message->message_id, 26);
+  tiny_codec_put_u32(data + 43, tiny_codec_crc32(data, 43));
+  return base64url_encode(data, sizeof(data), output, CURSOR_TEXT_MAX) == 63;
+}
+
+static bool
+cursor_decode(const char *session, const char *value, history_cursor_t *cursor)
+{
+  unsigned char data[CURSOR_BYTES];
+  if (!value || !value[0] || !base64url_decode(value, data) || data[0] != 1
+      || tiny_codec_get_u64(data + 1) != session_hash(session)
+      || tiny_codec_get_u32(data + 43) != tiny_codec_crc32(data, 43))
+    {
+      return false;
+    }
+  memcpy(cursor->message_id, data + 17, 26);
+  cursor->message_id[26] = '\0';
+  cursor->timestamp = (int64_t)tiny_codec_get_u64(data + 9);
+  return cursor->timestamp >= 0 && tiny_message_id_valid(cursor->message_id);
+}
+
+static int
+compare_cursor(const tiny_message_t *message, const history_cursor_t *cursor)
+{
+  if (message->timestamp_ms < cursor->timestamp)
     {
       return -1;
     }
-  if (a->message.timestamp_ms > b->message.timestamp_ms)
+  if (message->timestamp_ms > cursor->timestamp)
     {
       return 1;
     }
-  return strcmp(a->message.message_id, b->message.message_id);
+  return strcmp(message->message_id, cursor->message_id);
+}
+
+static size_t
+escaped_size(const char *value, size_t length)
+{
+  size_t position, total = 0;
+  for (position = 0; position < length; ++position)
+    {
+      unsigned char byte = (unsigned char)value[position];
+      total += byte < 0x20 ? 6 : (byte == '"' || byte == '\\' ? 2 : 1);
+    }
+  return total;
 }
 
 static void
@@ -29,52 +190,139 @@ call_read_messages(const mcpc_tool_t *tool, mcpc_ucbr_t *result)
 {
   tiny_mcp_tools_context_t *context = tiny_mcp_tools_context_current();
   char *session = tiny_mcp_tool_get_string(tool, "session_id", TINY_SESSION_ID_MAX);
-  const tiny_store_entry_t **items = NULL;
-  size_t index, count = 0;
+  char *cursor_text = tiny_mcp_tool_get_string(tool, "cursor", CURSOR_TEXT_MAX);
+  int32_t requested_limit = READ_DEFAULT_LIMIT;
+  mcpc_errcode_t limit_status
+      = mcpc_tool_get_tpropval_i32(tool, (const char8_t *)"limit", &requested_limit);
+  const size_t *entries = NULL;
+  size_t entry_count = 0, position = 0, emitted = 0, outer_size = 256;
+  history_cursor_t cursor;
+  bool has_cursor = cursor_text != NULL, more = false;
+  const tiny_message_t *last = NULL;
   tiny_json_buffer_t json;
-  if (!context || !session || !session[0])
+
+  if (!context || !session || !session[0]
+      || (limit_status != MCPC_EC_0 && limit_status != MCPC_EC_ANYDATA_NOTFOUND)
+      || requested_limit < 1 || requested_limit > READ_MAX_LIMIT
+      || (has_cursor && !cursor_decode(session, cursor_text, &cursor)))
     {
+      tiny_mcp_tool_add_error(result, "VALIDATION_ERROR", "invalid read_messages arguments");
       free(session);
-      tiny_mcp_tool_add_error(result, "VALIDATION_ERROR", "session_id is required");
+      free(cursor_text);
       return;
     }
-  items = malloc((tiny_store_entry_count(context->store) + 1) * sizeof(*items));
-  if (!items)
+  if (!tiny_mcp_tools_ensure_history_index(context)
+      || !tiny_history_index_session(context->history_index, session, &entries, &entry_count))
     {
+      tiny_mcp_tool_add_error(result, "INTERNAL_ERROR", "history index allocation failed");
       free(session);
-      tiny_mcp_tool_add_error(result, "INTERNAL_ERROR", "out of memory");
+      free(cursor_text);
       return;
     }
-  for (index = 0; index < tiny_store_entry_count(context->store); ++index)
+  if (has_cursor)
     {
-      const tiny_store_entry_t *entry = tiny_store_entry(context->store, index);
-      if (!entry->deleted && strcmp(entry->message.session_id, session) == 0)
+      size_t low = 0, high = entry_count;
+      while (low < high)
         {
-          items[count++] = entry;
+          size_t middle = low + (high - low) / 2;
+          const tiny_store_entry_t *entry = tiny_store_entry(context->store, entries[middle]);
+          if (compare_cursor(&entry->message, &cursor) <= 0)
+            {
+              low = middle + 1;
+            }
+          else
+            {
+              high = middle;
+            }
         }
+      position = low;
     }
-  qsort(items, count, sizeof(*items), compare_history);
+
   tiny_json_init(&json);
   tiny_json_raw(&json, "{\"history\":[");
-  for (index = 0; index < count; ++index)
+  while (position < entry_count && emitted < (size_t)requested_limit)
     {
-      if (index)
+      const tiny_store_entry_t *entry = tiny_store_entry(context->store, entries[position]);
+      tiny_json_buffer_t item;
+      size_t item_size;
+      if (!entry || entry->deleted)
+        {
+          position++;
+          continue;
+        }
+      tiny_json_init(&item);
+      tiny_mcp_tool_append_message(&item, &entry->message);
+      item_size = escaped_size(item.data, item.length) + (emitted ? 2 : 0);
+      if (item.failed || (emitted && outer_size + item_size > READ_RESPONSE_BUDGET))
+        {
+          tiny_json_free(&item);
+          if (item.failed)
+            {
+              json.failed = true;
+            }
+          more = true;
+          break;
+        }
+      if (emitted)
         {
           tiny_json_raw(&json, ",");
         }
-      tiny_mcp_tool_append_message(&json, &items[index]->message);
+      tiny_json_raw_n(&json, item.data, item.length);
+      outer_size += item_size;
+      emitted++;
+      last = &entry->message;
+      position++;
+      tiny_json_free(&item);
+    }
+  if (!more)
+    {
+      size_t lookahead = position;
+      while (lookahead < entry_count)
+        {
+          const tiny_store_entry_t *entry = tiny_store_entry(context->store, entries[lookahead++]);
+          if (entry && !entry->deleted)
+            {
+              more = true;
+              break;
+            }
+        }
+    }
+  tiny_json_raw(&json, "]");
+  if (more && last)
+    {
+      char next_cursor[CURSOR_TEXT_MAX];
+      if (!cursor_encode(session, last, next_cursor))
+        {
+          json.failed = true;
+        }
+      else
+        {
+          tiny_json_raw(&json, ",\"nextCursor\":");
+          tiny_json_string(&json, next_cursor);
+        }
+    }
+  tiny_json_raw(&json, "}");
+  if (json.failed)
+    {
+      tiny_mcp_tool_add_error(result, "INTERNAL_ERROR", "response allocation failed");
+    }
+  else
+    {
+      tiny_mcp_tool_add_json(result, &json);
     }
-  tiny_json_raw(&json, "]}");
-  tiny_mcp_tool_add_json(result, &json);
   tiny_json_free(&json);
-  free(items);
   free(session);
+  free(cursor_text);
 }
 
 bool
 tiny_mcp_register_read_messages(mcpc_server_t *server)
 {
-  mcpc_tool_t *tool = tiny_mcp_tool_new("read_messages", "Read a session", call_read_messages);
+  mcpc_tool_t *tool = tiny_mcp_tool_new("read_messages", "Read a session page", call_read_messages);
   return tool && tiny_mcp_tool_add_property(tool, "session_id", "Session ID", MCPC_U8STR, true)
+         && tiny_mcp_tool_add_property(
+             tool, "limit", "Optional page limit from 1 to 1000; defaults to 100", MCPC_I32, false)
+         && tiny_mcp_tool_add_property(
+             tool, "cursor", "Optional opaque page cursor", MCPC_U8STR, false)
          && mcpc_server_add_tool(server, tool) == MCPC_EC_0;
 }