Gemini CLI

Gemini CLI keeps a prompt-history log alongside active JSONL and legacy JSON chat files. Normal search reads the prompt log; --exhaustive also projects prompts from the chat files. The prompt-log adapter has no proof-bound targeted route, so --deep does not select Gemini conversations.

Base path: ~/.gemini (env override: GEMINI_CLI_HOME).

observed_version: gemini-cli v0.47.0 stable (observed 2026-06-21); types pinned at HEAD 927170fc.

Stores

default store
default store
Role:

primary_chat

Format:

jsonl

Coverage:

default_search

Adapter:

gemini.tmp_chats_jsonl.v1

Role:

supplementary_chat

Format:

json_object

Coverage:

catalog_only

Adapter:

-

default store
default store
Role:

prompt_history

Format:

json_array

Coverage:

default_search

Adapter:

gemini.tmp_logs_json.v1

Role:

supplementary_chat

Format:

json_object

Coverage:

default_search

Adapter:

gemini.tmp_chats_legacy_json.v1

catalog store
catalog store
Role:

app_state

Format:

md_frontmatter

Coverage:

catalog_only

Adapter:

-

catalog store
catalog store
Role:

app_state

Format:

json_object

Coverage:

catalog_only

Adapter:

-

inspectable store
inspectable store
Role:

persistent_memory

Format:

text

Coverage:

inspectable

Adapter:

gemini.memory_text.v1

inspectable store
inspectable store
Role:

app_state

Format:

text

Coverage:

inspectable

Adapter:

gemini.tool_outputs_text.v1

gemini.tmp.chats

gemini.tmp.chats
default store
default store
gemini.tmp.chats

JSONL with mixed record types. Line 1 is a SessionMetadataRecord (sessionId, projectHash, startTime, lastUpdated, kind). Subsequent lines are MessageRecord turns (id, timestamp, type, content, optional toolCalls/thoughts/tokens/model/displayContent) interleaved with MetadataUpdateRecord updates ({$set: ...}). content is the searched (expanded) form; the occasional displayContent key is the UI-echo variant. Upstream types also declare RewindRecord and PartialMetadataRecord plus type values info/error/warning. The CLI does write info/error system records, but agentgrep surfaces only the user and gemini conversation turns and skips the system records. Adapter store field uses the underscore-flattened form gemini.tmp_chats.

Agent:

Gemini

Role:

primary_chat

Format:

jsonl

Coverage:

default_search

Path:

${GEMINI_CLI_HOME or ${HOME}/.gemini}/tmp/<project_hash>/chats/session-<timestamp><id>.jsonl

Adapter:

gemini.tmp_chats_jsonl.v1

Data version:

-

Version strategies:

-

Observed:

gemini-cli v0.47.0 stable (2026-06-21)

Default search:

yes

Parsed by agentgrep via parse_gemini_chat_file (gemini.tmp_chats_jsonl.v1). When a gemini-typed record’s content is empty, the assistant’s prose is drawn from thoughts[*].subject/description and the tool-call context from toolCalls[*].name/description — concatenated into one SearchRecord per turn.

gemini.tmp.checkpoints

gemini.tmp.checkpoints
catalog store
catalog store
gemini.tmp.checkpoints

Single-file conversation snapshot written by the /chat save command. JSON object { history: Content[]; authType?: AuthType } where each Content is {role: 'user'|'model', parts: [...]}.

Agent:

Gemini

Role:

supplementary_chat

Format:

json_object

Coverage:

catalog_only

Path:

${GEMINI_CLI_HOME or ${HOME}/.gemini}/tmp/<project_hash>/chats/checkpoint-<tag>.json

Adapter:

-

Data version:

-

Version strategies:

-

Observed:

gemini-cli v0.47.0 stable (2026-06-21)

Default search:

no

User-named snapshots vs. continuous transcript.

gemini.tmp.logs

gemini.tmp.logs
default store
default store
gemini.tmp.logs

JSON array of LogEntry { sessionId, messageId, timestamp, type, message } — user-prompt audit log. Adapter store field uses the underscore-flattened form gemini.tmp_logs.

Agent:

Gemini

Role:

prompt_history

Format:

json_array

Coverage:

default_search

Path:

${GEMINI_CLI_HOME or ${HOME}/.gemini}/tmp/<project_hash>/logs.json

Adapter:

gemini.tmp_logs_json.v1

Data version:

-

Version strategies:

-

Observed:

gemini-cli v0.47.0 stable (2026-06-21)

Default search:

yes

Parsed by agentgrep via parse_gemini_logs_file (gemini.tmp_logs_json.v1).

gemini.tmp.chats_legacy

gemini.tmp.chats_legacy
default store
default store
gemini.tmp.chats_legacy

Pre-Feb 2026 single-file session format. JSON object with top-level sessionId, projectHash, startTime, lastUpdated, and a messages array carrying the same per-turn fields as the current JSONL format. Upstream still reads this shape via the isLegacyRecord discriminator. Adapter store field uses the underscore-flattened form gemini.tmp_chats_legacy.

Agent:

Gemini

Role:

supplementary_chat

Format:

json_object

Coverage:

default_search

Path:

${GEMINI_CLI_HOME or ${HOME}/.gemini}/tmp/<project_hash>/chats/session-<timestamp><id>.json

Adapter:

gemini.tmp_chats_legacy_json.v1

Data version:

-

Version strategies:

-

Observed:

gemini-cli v0.47.0 stable (2026-06-21)

Default search:

yes

Parsed by agentgrep via parse_gemini_chat_legacy_file (gemini.tmp_chats_legacy_json.v1). Covers sessions whose files predate the JSONL migration; upstream still handles them.

gemini.skills

gemini.skills
catalog store
catalog store
gemini.skills

Skill definitions; not chat.

Agent:

Gemini

Role:

app_state

Format:

md_frontmatter

Coverage:

catalog_only

Path:

${GEMINI_CLI_HOME or ${HOME}/.gemini}/skills/

Adapter:

-

Data version:

-

Version strategies:

-

Observed:

gemini-cli v0.47.0 stable (2026-06-21)

Default search:

no

gemini.settings

gemini.settings
catalog store
catalog store
gemini.settings

Configuration; not chat.

Agent:

Gemini

Role:

app_state

Format:

json_object

Coverage:

catalog_only

Path:

${GEMINI_CLI_HOME or ${HOME}/.gemini}/settings.json

Adapter:

-

Data version:

-

Version strategies:

-

Observed:

gemini-cli v0.47.0 stable (2026-06-21)

Default search:

no

gemini.memory

gemini.memory
inspectable store
inspectable store
gemini.memory

Global user-authored context/memory Markdown injected into Gemini CLI sessions — the Gemini analogue of Claude’s CLAUDE.md. Standing instructions, not chat; inspectable opt-in rather than searched by default.

Agent:

Gemini

Role:

persistent_memory

Format:

text

Coverage:

inspectable

Path:

${GEMINI_CLI_HOME or ${HOME}/.gemini}/GEMINI.md

Adapter:

gemini.memory_text.v1

Data version:

gemini.memory.markdown.v1

Version strategies:

shape_inference, catalog_observation

Observed:

gemini-cli v0.47.0 stable (2026-06-21)

Default search:

no

gemini.tool_outputs

gemini.tool_outputs
inspectable store
inspectable store
gemini.tool_outputs

Per-tool-call output text (run_shell_command / read_file / update_topic results) under tmp/<hash>/tool-outputs/session-<id>/. Tool output rather than user prompts (may echo file or command content), so inspectable opt-in, not searched by default.

Agent:

Gemini

Role:

app_state

Format:

text

Coverage:

inspectable

Path:

${GEMINI_CLI_HOME or ${HOME}/.gemini}/tmp/<project_hash>/tool-outputs/session-<id>/<name>.txt

Adapter:

gemini.tool_outputs_text.v1

Data version:

-

Version strategies:

-

Observed:

gemini-cli v0.47.0 stable (2026-06-21)

Default search:

no

Record schemas

Active chat JSONL

gemini.tmp.chats is JSONL with mixed record types. Line 1 is a SessionMetadataRecord (sessionId, projectHash, startTime, lastUpdated, kind). Subsequent lines are MessageRecord turns (id, timestamp, type, content) interleaved with MetadataUpdateRecord updates ({$set: {...}}). Some user records also carry displayContent (the UI-echo variant); content is the expanded form agentgrep searches.

For gemini-typed records whose content is empty, the assistant’s prose is drawn from thoughts[*].subject/description and the tool-call context from toolCalls[*].name/description.

Legacy chat JSON

gemini.tmp.chats_legacy is the pre-Feb 2026 single-file .json format. It is a JSON object with session metadata at the top level and the full conversation under a messages array.

Prompt logs

gemini.tmp.logs is a flat JSON array of LogEntry { sessionId, messageId, timestamp, type, message } — a user-prompt audit log.

Memory file

gemini.memory is ~/.gemini/GEMINI.md — the global user-authored context/memory file injected into Gemini CLI sessions, the analogue of Claude’s CLAUDE.md. Standing instructions rather than chat, so it is inspectable (opt-in) rather than searched by default.

Path hashing

Legacy tmp/ project directories are named by the SHA-256 of the project root; current Gemini CLI also uses timestamp-style and plain project-basename directory names. Discovery does not depend on the scheme — agentgrep walks tmp/ recursively — but agentgrep still exposes gemini_project_hash() to reproduce the legacy hash directories.

Project context

Store

model

cwd

branch

gemini.tmp.chats

assistant turn’s model

metadata line’s directories[0], else sibling .project_root

gemini.tmp.chats_legacy

sibling .project_root

gemini.tmp.logs

sibling .project_root

All three prompt stores live under tmp/<project_hash>/, so the directory name gives every record its origin.cwd_hash. The literal path is on disk too, in two places: the session metadata line names it in a plural directories array — where every other agent writes a scalar cwd — and Gemini drops a .project_root file next to the hashed directory. agentgrep reads both, so Gemini records carry cwd and cwd_hash together and answer --cwd, cwd:, repo:, and project: alongside cwd_hash:. Both sources are lossless; a missing .project_root is ordinary on older trees and simply leaves the record without a cwd.

Gemini records no git branch in any of its prompt stores, so branch: does not reach this backend.