ZacharyZhang-NY
dc9cfb5a30
A memory used to have one state: present. A session could not be reloaded
without searching, nothing separated what a person said today from what the
store ingested a year ago, and two statements that disagree about a number
were both handed to the reader as if the store believed both.
Schema v10. Atoms gain session_id, importance, recall_count, last_recalled_at
and archived_at; two tables arrive beside them — consolidations (one watermark
per holder+scenario lane) and conflicts (a pair, the term they disagree on,
both values, and whether anyone has settled it). v_atoms_current now also
hides archived rows, and apply() drops the view before rebuilding it because
CREATE VIEW IF NOT EXISTS would keep the old body and ignore the archive.
Working memory is a read, not a store: `working <holder> <session>` returns
what that session recorded, in order, with no search involved. Consolidation
rolls a lane's new memories into one standing summary and moves the watermark
to the newest memory actually rolled up — not to the clock of the pass, which
made a second pass count the same memories twice. The archive rule is stated
in the command that runs it (recorded before N days, never returned by a
search, importance at or under a floor) rather than hidden in a decay formula
nobody measured; --dry-run names the victims first.
A conflict is recorded when a new memory repeats a label with a different
number in the same holder's same scenario. Retrieval drops the older side
while the conflict is open and both sides answer again once it is settled:
settling is not superseding, and a word-only disagreement is left alone
because a reworded sentence would fire on every paraphrase. Numbers are keyed
to both the memory's subject and the nearest preceding label, measured: the
two thermostat sentences share only their subject, so a nearest-word-only rule
found nothing.
Search now counts the memories it handed back, which is the only use estimate
the store has, and the archive rule reads it. The dense index applies the same
currency rules as the view, so an archived memory cannot stay findable through
one leg while the other hides it.
Two reads over HTTP (working, conflicts) and two tools over MCP
(working_set, memory_conflicts); curation stays with the operator because an
agent should not decide what its own past is worth. remember and supersede
carry a session id; importance does not cross MCP, because recall_count is
observed and importance is stated.
Gates: 366 passed; ruff clean; mypy 24 errors in 9 files, the recorded 9cb46c1
baseline, net 0; pyright 0 on the touched files; go build/vet/test and gofmt
clean; mcp_write_smoke PASS.
90 lines
3.3 KiB
Go
90 lines
3.3 KiB
Go
package mcpserver
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"io"
|
|
"os"
|
|
"path/filepath"
|
|
"strings"
|
|
|
|
"github.com/ZacharyZhang-NY/ely-eye/ely-eye-mcp/internal/apiclient"
|
|
"github.com/ZacharyZhang-NY/ely-eye/ely-eye-mcp/internal/config"
|
|
"github.com/ZacharyZhang-NY/ely-eye/ely-eye-mcp/internal/store"
|
|
"github.com/modelcontextprotocol/go-sdk/mcp"
|
|
)
|
|
|
|
type Server struct {
|
|
cfg config.Config
|
|
store *store.Store
|
|
api *apiclient.Client
|
|
version string
|
|
}
|
|
|
|
func Run(ctx context.Context, cfg config.Config, version string) error {
|
|
db, err := store.Open(ctx, cfg)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
defer db.Close()
|
|
server := &Server{cfg: cfg, store: db, api: apiclient.New(cfg.APIBaseURL), version: version}
|
|
mcpServer := mcp.NewServer(&mcp.Implementation{
|
|
Name: "ely-eye",
|
|
Title: "Ely-Eye Context Cartridge MCP",
|
|
Version: version,
|
|
}, &mcp.ServerOptions{
|
|
Instructions: "Use Ely-Eye tools to retrieve local cartridge context, evidence atoms, proof suites, and compiled evidence packs. Read tools mirror local Ely-Eye state without writing. remember, supersede_memory and forget_memory mutate memory through the Ely-Eye API, which must be running (`ely-eye serve`); the server, not the caller, decides who owns a memory. mount_cartridge and switch_cartridge decide what a search may see: mount a cartridge to ask only that cartridge, and unmount everything to ask the whole library. working_set reloads what one session already recorded, in order, without searching; memory_conflicts reports what the store has not reconciled, and settling one is the operator's act, not a tool's.",
|
|
})
|
|
server.registerTools(mcpServer)
|
|
server.registerWriteTools(mcpServer)
|
|
server.registerDirectoryTools(mcpServer)
|
|
server.registerMountTools(mcpServer)
|
|
server.registerTierTools(mcpServer)
|
|
server.registerResources(mcpServer)
|
|
if err := mcpServer.Run(ctx, &mcp.StdioTransport{}); err != nil {
|
|
if errors.Is(err, io.EOF) || strings.HasSuffix(err.Error(), "EOF") {
|
|
return nil
|
|
}
|
|
return err
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func (s *Server) registerResources(server *mcp.Server) {
|
|
addFileResource(server, "ely-eye://project/prd", "Ely-Eye PRD", filepath.Join(s.cfg.ProjectRoot, "PRD.md"))
|
|
addFileResource(server, "ely-eye://project/readme", "Ely-Eye README", filepath.Join(s.cfg.ProjectRoot, "README.md"))
|
|
addFileResource(server, "ely-eye://project/mcp-research", "Ely-Eye MCP research notes", filepath.Join(s.cfg.ProjectRoot, "ely-eye-mcp", "docs", "RESEARCH.md"))
|
|
}
|
|
|
|
// addFileResource registers a project document only when it exists on disk.
|
|
// External deployments rarely ship the Ely-Eye repository documents, so a
|
|
// missing file is a normal condition and the resource is simply omitted.
|
|
func addFileResource(server *mcp.Server, uri string, name string, path string) {
|
|
info, err := os.Stat(path)
|
|
if err != nil {
|
|
return
|
|
}
|
|
size := info.Size()
|
|
server.AddResource(&mcp.Resource{
|
|
URI: uri,
|
|
Name: name,
|
|
Title: name,
|
|
Description: "Local Ely-Eye project resource: " + path,
|
|
MIMEType: "text/markdown",
|
|
Size: size,
|
|
}, func(ctx context.Context, request *mcp.ReadResourceRequest) (*mcp.ReadResourceResult, error) {
|
|
_ = ctx
|
|
data, err := os.ReadFile(path)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
return &mcp.ReadResourceResult{
|
|
Contents: []*mcp.ResourceContents{{
|
|
URI: request.Params.URI,
|
|
MIMEType: "text/markdown",
|
|
Text: string(data),
|
|
}},
|
|
}, nil
|
|
})
|
|
}
|