feat: extract groups from message logs

This commit is contained in:
zhaoyilun
2026-07-09 23:42:56 +08:00
parent 7e616a1f10
commit 4502a05bb4
4 changed files with 172 additions and 4 deletions

View File

@@ -19,7 +19,7 @@ Schema notes: `docs/source-discovery/2026-07-09-n12-pre-zyl-schema-notes.md`
| --- | --- | --- | --- | --- | --- | | --- | --- | --- | --- | --- | --- |
| `isphere_receive_messages` | decrypted `PacketReader.ProcessPacket` XMPP `<message>` stanzas via `internal/isphere.EncryptedPacketLogSource` | decrypted `Smark.SendReceive` transport stanzas; decrypted `SaveToDB` `Chat_OnMessageArrived` traces; wrapped `MsgLib.db` after DB wrapper is solved | `docs/source-discovery/2026-07-09-n12-pre-zyl-schema-notes.md#field-mapping-evidence` | C5 env loader wired through ISPHERE_PACKET_LOG_FILE; default source remains empty when unset | fixture-backed configured-source operator smoke | | `isphere_receive_messages` | decrypted `PacketReader.ProcessPacket` XMPP `<message>` stanzas via `internal/isphere.EncryptedPacketLogSource` | decrypted `Smark.SendReceive` transport stanzas; decrypted `SaveToDB` `Chat_OnMessageArrived` traces; wrapped `MsgLib.db` after DB wrapper is solved | `docs/source-discovery/2026-07-09-n12-pre-zyl-schema-notes.md#field-mapping-evidence` | C5 env loader wired through ISPHERE_PACKET_LOG_FILE; default source remains empty when unset | fixture-backed configured-source operator smoke |
| `isphere_search_contacts` | bare sender/receiver JIDs extracted from normalized log-backed messages | decrypted roster/contact stanzas from `Smark.SendReceive`; `MsgLib.db` contact/conversation tables after DB wrapper is solved; UIA helper source if display names are missing | `docs/source-discovery/2026-07-09-n12-pre-zyl-schema-notes.md#log-decryption-result` | C8 MCP tool registered and verify-go-mcp covers default/configured contact smoke; JID-only display/account fallback | enrich display names from roster/db/uia evidence | | `isphere_search_contacts` | bare sender/receiver JIDs extracted from normalized log-backed messages | decrypted roster/contact stanzas from `Smark.SendReceive`; `MsgLib.db` contact/conversation tables after DB wrapper is solved; UIA helper source if display names are missing | `docs/source-discovery/2026-07-09-n12-pre-zyl-schema-notes.md#log-decryption-result` | C8 MCP tool registered and verify-go-mcp covers default/configured contact smoke; JID-only display/account fallback | enrich display names from roster/db/uia evidence |
| `isphere_search_groups` | decrypted `PacketReader.ProcessPacket` `type="groupchat"` stanzas and conference/MUC JIDs | `MsgLib.db` group/conversation tables after DB wrapper is solved; UIA helper source if group display names are missing | C9 ignored-log scan: PacketReader 86 groupchat/86 conference hits; Smark 24 groupchat/658 conference/631 muc hits | C9 evidence confirmed; display names still unavailable | implement group candidate extraction from normalized messages | | `isphere_search_groups` | decrypted `PacketReader.ProcessPacket` `type="groupchat"` stanzas and conference/MUC JIDs | `MsgLib.db` group/conversation tables after DB wrapper is solved; UIA helper source if group display names are missing | C9 ignored-log scan: PacketReader 86 groupchat/86 conference hits; Smark 24 groupchat/658 conference/631 muc hits | C10 source extraction unit-verified with JID-only display fallback | register MCP tool from C10 source |
| `isphere_receive_files` | decrypted `PacketReader.ProcessPacket` file-transfer message stanzas plus `zyl\importal\<hash>` cache mapping | decrypted `Smark.SendReceive` and `SaveToDB` traces for file-reference reconciliation | `docs/source-discovery/2026-07-09-n12-pre-zyl-schema-notes.md#field-mapping-evidence` | candidate pending cache-reference mapping | fourth | | `isphere_receive_files` | decrypted `PacketReader.ProcessPacket` file-transfer message stanzas plus `zyl\importal\<hash>` cache mapping | decrypted `Smark.SendReceive` and `SaveToDB` traces for file-reference reconciliation | `docs/source-discovery/2026-07-09-n12-pre-zyl-schema-notes.md#field-mapping-evidence` | candidate pending cache-reference mapping | fourth |
## Stage C entry rule ## Stage C entry rule

View File

@@ -1103,7 +1103,7 @@ Evidence precheck result:
- Search query matches group JID/display name case-insensitively. - Search query matches group JID/display name case-insensitively.
- This loop does not register `isphere_search_groups`; registration comes after source behavior passes tests. - This loop does not register `isphere_search_groups`; registration comes after source behavior passes tests.
- [ ] **Step 1: Write failing group extraction test** - [x] **Step 1: Write failing group extraction test**
Create `internal/isphere/groups_test.go` and run: Create `internal/isphere/groups_test.go` and run:
@@ -1113,11 +1113,11 @@ go test ./internal/isphere -run TestSearchGroupsFromMessagesMatchesGroupchatJIDs
Expected initial failure: group search types/functions do not exist. Expected initial failure: group search types/functions do not exist.
- [ ] **Step 2: Implement group extraction/search** - [x] **Step 2: Implement group extraction/search**
Create `internal/isphere/groups.go` with minimal pure Go logic over normalized messages and synthetic groupchat fixtures. Create `internal/isphere/groups.go` with minimal pure Go logic over normalized messages and synthetic groupchat fixtures.
- [ ] **Step 3: Run full verification and rewrite Loop C11** - [x] **Step 3: Run full verification and rewrite Loop C11**
Run: Run:
@@ -1132,6 +1132,71 @@ Expected: all exit 0. Remove any generated root `isphere-mcp.exe` after build. R
--- ---
## Loop C10 Result
Implemented and verified in this loop:
- `internal/isphere.SearchGroupsFromMessages(messages, query)` extracts unique group candidates from normalized messages with `ConversationType == "groupchat"` or conference/MUC/group JID markers.
- Groups currently use the group bare JID as `GroupID` and `DisplayName`; `Source` is `local_readonly`, `Confidence` is `0.6`, and `RawRef` is `groupchat_jid` until richer group roster/display-name evidence is validated.
- Query matching is case-insensitive over group JID/display name and `Limit` truncates deterministic sorted results.
- Verification completed for C10 with the loop-specific test; full verification is run again before commit.
---
## Loop C11: Register `isphere_search_groups` MCP tool
**Goal:** Register the group search MCP tool on top of the C10 group extraction behavior while keeping display/member fields clearly marked as JID-derived/unknown.
**Planned files:**
- Create: `internal/tools/isphere_groups.go`
- Create: `internal/tools/isphere_groups_test.go`
- Modify: `internal/mcpserver/server.go`
- Modify: `internal/mcpserver/server_test.go`
- Modify: `scripts/verify-go-mcp.ps1`
- Modify: `docs/go-mcp-runbook.md`
- Modify: `docs/current-status-card.md`
- Modify: `docs/superpowers/plans/2026-07-09-stage-c-log-backed-receive-messages-loop.md`
**Planned interface:**
- Tool name: `isphere_search_groups`.
- Input: `query`, `limit`.
- Source: group extraction over the same env-configured message source used by receive/contact tools.
- Output shape: `ok`, `groups`, `next_cursor`, `audit` minimal fields aligned with `docs/mcp-core-tools-contract.md`.
- Default empty source returns `ok: true`, `groups: []`.
- [ ] **Step 1: Write failing tool test**
Create `internal/tools/isphere_groups_test.go` and run:
```powershell
go test ./internal/tools -run TestISphereSearchGroupsToolReturnsJIDGroups -v
```
Expected initial failure: group tool registration does not exist.
- [ ] **Step 2: Implement group tool registration**
Register `isphere_search_groups` with source injection for tests. Use C10 source behavior and return a contract-shaped map with minimal audit metadata.
- [ ] **Step 3: Wire server and verification**
Register group search in server construction. Update server tool-count tests and `scripts/verify-go-mcp.ps1` to expect seven tools and call `isphere_search_groups` against default empty source and synthetic configured groupchat fixture.
- [ ] **Step 4: Run full verification and commit**
Run:
```powershell
git diff --check
go test ./...
go build ./cmd/isphere-mcp
powershell -NoProfile -ExecutionPolicy Bypass -File scripts/verify-go-mcp.ps1
```
Expected: all exit 0. Remove any generated root `isphere-mcp.exe` after build. Commit exact C11 paths only and rewrite the next loop from actual results.
---
## Self-Review ## Self-Review
- Spec coverage: the plan follows the user's cyclic requirement: plan first, implement one loop at a time, update the next loop after each result, and ask only on blockers. - Spec coverage: the plan follows the user's cyclic requirement: plan first, implement one loop at a time, update the next loop after each result, and ask only on blockers.

View File

@@ -0,0 +1,81 @@
package isphere
import (
"sort"
"strings"
)
type Group struct {
GroupID string
DisplayName string
Source string
Confidence float64
RawRef string
}
type SearchGroupsQuery struct {
Query string
Limit int
}
type SearchGroupsResult struct {
Groups []Group
}
func SearchGroupsFromMessages(messages []Message, query SearchGroupsQuery) SearchGroupsResult {
unique := map[string]Group{}
for _, message := range messages {
if strings.EqualFold(message.ConversationType, "groupchat") {
addMessageGroup(unique, message.SenderID)
addMessageGroup(unique, message.ReceiverID)
continue
}
if isLikelyGroupJID(message.SenderID) {
addMessageGroup(unique, message.SenderID)
}
if isLikelyGroupJID(message.ReceiverID) {
addMessageGroup(unique, message.ReceiverID)
}
}
queryText := strings.ToLower(strings.TrimSpace(query.Query))
ids := make([]string, 0, len(unique))
for id := range unique {
if queryText == "" || strings.Contains(strings.ToLower(id), queryText) || strings.Contains(strings.ToLower(unique[id].DisplayName), queryText) {
ids = append(ids, id)
}
}
sort.Strings(ids)
limit := query.Limit
if limit <= 0 || limit > len(ids) {
limit = len(ids)
}
groups := make([]Group, 0, limit)
for _, id := range ids[:limit] {
groups = append(groups, unique[id])
}
return SearchGroupsResult{Groups: groups}
}
func addMessageGroup(unique map[string]Group, id string) {
trimmed := strings.TrimSpace(id)
if trimmed == "" || !isLikelyGroupJID(trimmed) {
return
}
if _, exists := unique[trimmed]; exists {
return
}
unique[trimmed] = Group{
GroupID: trimmed,
DisplayName: trimmed,
Source: "local_readonly",
Confidence: 0.6,
RawRef: "groupchat_jid",
}
}
func isLikelyGroupJID(id string) bool {
lower := strings.ToLower(strings.TrimSpace(id))
return strings.Contains(lower, "conference") || strings.Contains(lower, "muc") || strings.Contains(lower, "group")
}

View File

@@ -0,0 +1,22 @@
package isphere
import (
"reflect"
"testing"
)
func TestSearchGroupsFromMessagesMatchesGroupchatJIDs(t *testing.T) {
messages := []Message{
{ID: "msg-1", ConversationType: "groupchat", SenderID: "project-room@conference.imopenfire1-lanzhou", ReceiverID: "user@imopenfire1-lanzhou"},
{ID: "msg-2", ConversationType: "chat", SenderID: "alice@imopenfire1-lanzhou", ReceiverID: "bob@imopenfire1-lanzhou"},
{ID: "msg-3", ConversationType: "groupchat", SenderID: "project-room@conference.imopenfire1-lanzhou", ReceiverID: "other@imopenfire1-lanzhou"},
}
got := SearchGroupsFromMessages(messages, SearchGroupsQuery{Query: "project", Limit: 10})
want := SearchGroupsResult{Groups: []Group{
{GroupID: "project-room@conference.imopenfire1-lanzhou", DisplayName: "project-room@conference.imopenfire1-lanzhou", Source: "local_readonly", Confidence: 0.6, RawRef: "groupchat_jid"},
}}
if !reflect.DeepEqual(got, want) {
t.Fatalf("SearchGroupsFromMessages() = %#v, want %#v", got, want)
}
}