admin/isphere-ai-bridge
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: harden search ranking and deduplication

Browse Source
This commit is contained in:
zhaoyilun
2026-07-10 09:39:18 +08:00
parent 1d6dd2f504
commit 6ca6c08b62
13 changed files with 368 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/go-mcp-runbook.md
View File

@@ -96,8 +96,8 @@ The verification confirms:
- `isphere_receive_messages` returns the contract-facing `ok`, `conversation`, `messages`, `next_cursor`, and `audit` envelope, while preserving legacy message aliases such as `id`, `text`, and `timestamp`.
- A synthetic configured-source smoke check proves `ISPHERE_PACKET_LOG_FILE` can drive `isphere_receive_messages` end-to-end with one redacted fixture message.
- A synthetic configured-directory smoke check proves `ISPHERE_PACKET_LOG_DIR` can drive `isphere_receive_messages`, contact search, group search, and file-list extraction from a temporary directory fixture.
- `isphere_search_contacts` is callable and returns JID-derived contact candidates from the same configured synthetic message fixture.
- `isphere_search_groups` is callable and returns JID-derived group candidates from the configured synthetic groupchat fixture.
- `isphere_search_contacts` is callable and returns JID-derived contact candidates from the same configured synthetic message fixture; exact ID/display/account matches rank before prefix/substring matches and case-insensitive duplicates are collapsed.
- `isphere_search_groups` is callable and returns JID-derived group candidates from the configured synthetic groupchat fixture; exact ID/display-name matches rank before prefix/substring matches and case-insensitive duplicates are collapsed.
- `isphere_receive_files` is callable in list mode and returns one file metadata candidate from the configured synthetic file-transfer fixture.
- Verification uses synthetic/local helper checks and does not load raw N12-pre evidence.
- The deterministic verification path clears MsgLib env variables, so it proves the default no-MsgLib behavior remains stable.
@@ -246,8 +246,8 @@ These eight tools are currently allowed:
| `win_helper_scan_windows` | helper `scan_windows` | Read visible window metadata or likely iSphere candidates. |
| `win_helper_dump_uia` | helper `dump_uia` | Read a UI Automation tree for a specified window handle. |
| `isphere_receive_messages` | log-backed `EncryptedPacketLogSource` | Read normalized messages from the configured PacketReader log source with a contract-shaped response envelope. The default server source is empty unless `ISPHERE_PACKET_LOG_FILE` or `ISPHERE_PACKET_LOG_DIR` is configured. |
| `isphere_search_contacts` | log-backed message JIDs | Search contact candidates extracted from sender/receiver bare JIDs in the configured message source. |
| `isphere_search_groups` | log-backed groupchat JIDs | Search group candidates extracted from groupchat/conference/MUC bare JIDs in the configured message source. |
| `isphere_search_contacts` | log-backed message JIDs plus optional MsgLib display enrichment | Search contact candidates extracted from sender/receiver bare JIDs in the configured message source, with deterministic exact-match-first ranking, case-insensitive de-duplication, and preserved `source`/`raw_ref`. |
| `isphere_search_groups` | log-backed groupchat JIDs plus optional MsgLib display enrichment | Search group candidates extracted from groupchat/conference/MUC bare JIDs in the configured message source, with deterministic exact-match-first ranking, case-insensitive de-duplication, and preserved `source`/`raw_ref`. |
| `isphere_receive_files` | log-backed file-transfer messages | List file metadata candidates extracted from file-transfer message bodies. Download/cache mapping is not implemented yet. |
Allowed parameters:
@@ -274,7 +274,7 @@ The current runbook verifies eight tools:
- `isphere_search_groups`
- `isphere_receive_files`
The current log-backed business read tools have parser/source/tool registration and an empty default server source. Raw N12-pre evidence remains under ignored `runs/` paths and is not committed. The current command entry point can read an operator-local encrypted PacketReader log-line file via `ISPHERE_PACKET_LOG_FILE` or a directory of `.log`/`.txt` files via `ISPHERE_PACKET_LOG_DIR`; this is still not a production ingestion claim because raw evidence remains local and uncommitted. `isphere_receive_messages` now exposes contract-facing fields for digital-employee consumption while preserving older aliases for compatibility, supports `conversation_id`, keyword `query`, and RFC3339 `since` filtering, and validates the remaining safe contract args without pretending unsupported connectors/pagination exist. Contact and group search also accept the safe local-readonly contract args and can optionally enrich display metadata from `MsgLibReadSidecar`; receive-message `sender_name` and `conversation.display_name` can use that same optional metadata when MsgLib env is configured. `isphere_receive_files` supports list mode with safe contract arg validation; download/cache mapping remains deferred.
The current log-backed business read tools have parser/source/tool registration and an empty default server source. Raw N12-pre evidence remains under ignored `runs/` paths and is not committed. The current command entry point can read an operator-local encrypted PacketReader log-line file via `ISPHERE_PACKET_LOG_FILE` or a directory of `.log`/`.txt` files via `ISPHERE_PACKET_LOG_DIR`; this is still not a production ingestion claim because raw evidence remains local and uncommitted. `isphere_receive_messages` now exposes contract-facing fields for digital-employee consumption while preserving older aliases for compatibility, supports `conversation_id`, keyword `query`, and RFC3339 `since` filtering, and validates the remaining safe contract args without pretending unsupported connectors/pagination exist. Contact and group search also accept the safe local-readonly contract args, rank exact matches before prefix/substring matches, collapse case-insensitive duplicates across log-derived candidates and optional `MsgLibReadSidecar` display metadata, and preserve `source`/`raw_ref`; receive-message `sender_name` and `conversation.display_name` can use that same optional metadata when MsgLib env is configured. `isphere_receive_files` supports list mode with safe contract arg validation; download/cache mapping remains deferred.
Core business tools for contacts, groups, messages, and files are defined in `docs/mcp-core-tools-contract.md`. Send capabilities enter the roadmap through that contract after source discovery, connector selection, preview metadata, execution metadata, and audit records are in place.