Compare commits

...

36 Commits

Author SHA1 Message Date
Sri Pasumarthi eb42ff6086 feat: promote Gemini 3.1 Flash Lite to GA and support Gemini 3.5 Flash 2026-06-11 13:33:53 -07:00
davidapierce a57f33acbc Update default flash lite tool model 2026-06-04 15:40:49 -07:00
gemini-cli-robot f54f63cd4c chore(release): v0.42.0-nightly.20260512.gc987b9939 2026-05-12 20:11:07 +00:00
Adam Weidman c987b99394 refactor(core): introduce SubagentState enum for progress (#26934) 2026-05-12 18:58:25 +00:00
Coco Sheng c4973d01da ci: actively triage missing priority labels and intelligently clean up conflicting labels (#26865) 2026-05-12 18:33:55 +00:00
kevinjwang1 27a39b04b0 Enable NumericalRouter when using dynamic model configs (#26929) 2026-05-12 18:06:21 +00:00
Sandy Tao ebe15553a9 Exclude extension context from skill extraction agent (#26879) 2026-05-12 10:45:19 -07:00
Yulong Wu bc730b2c0f fix (telemetry): inject quota_project_id to prevent fallback to default oauth client (#26698)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Tommaso Sciortino <sciortino@gmail.com>
2026-05-12 17:02:15 +00:00
Gal Zahavi 9fe8643552 chore: update checkout action configuration in workflows (#26897) 2026-05-12 16:58:37 +00:00
joshualitt 07792f98cd feat(context): Introduce adaptive token calculator to more accurately calculate content sizes. (#26888) 2026-05-12 15:51:20 +00:00
Coco Sheng 7a9ed4c20a fix: respect explicit model selection after Flash quota exhaustion (#26759) (#26872) 2026-05-12 14:26:50 +00:00
Kuroda Kayn 11a9edc808 fix(cli): restore resume for legacy sessions (#26577)
Co-authored-by: Tommaso Sciortino <sciortino@gmail.com>
2026-05-12 00:28:47 +00:00
Adam Weidman 24b98ade86 fix(cli): enable adk non-interactive session (#26895) 2026-05-11 23:38:23 +00:00
Eswar809 9f759f97a2 fix(core): ignore .pak and .rpa game archive formats by default (#26884)
Co-authored-by: Tommaso Sciortino <sciortino@gmail.com>
2026-05-11 21:58:08 +00:00
Franco Pieri 9ff7304391 Allow Enter to select session while in search mode in /resume (#21523)
Co-authored-by: Tommaso Sciortino <sciortino@gmail.com>
2026-05-11 21:46:00 +00:00
Neil Nair 84fc5cd533 Fix/vscode run current file ts (#22894)
Co-authored-by: Spencer <spencertang@google.com>
2026-05-11 21:21:42 +00:00
Daniel Weis e1b3ce5b36 revert 6b9b778d82 (#26893) 2026-05-11 21:07:54 +00:00
Suhaan Raqeeb Khavas 8e58df72c6 fix: prevent EISDIR crash when customIgnoreFilePaths contains directories (#19868) (#19898)
Co-authored-by: Tommaso Sciortino <sciortino@gmail.com>
2026-05-11 20:46:08 +00:00
Dev Randalpura c0d5ab1f1e fix(ui): added a gutter width to the input prompt width calculation (#26882) 2026-05-11 20:26:48 +00:00
Coco Sheng 1340c96071 fix(core): handle malformed projects.json in ProjectRegistry (#26885) 2026-05-11 20:19:01 +00:00
Daniel Weis f8198a25d8 fix(routing): Refactor tool turn handling for the conversation history in NumericalClassifierStrategy to prevent 400 Bad Request (#26761) 2026-05-11 20:09:38 +00:00
Coco Sheng 36a7fa089c fix(cli): use static tool name in confirmation prompt to avoid parsing errors (#26866) 2026-05-11 17:45:58 +00:00
Sri Pasumarthi 4739495e39 fix(cli/acp): prevent infinite thought loop in ACP mode by disablig nextSpeakerCheck (#26874) 2026-05-11 17:38:20 +00:00
Aryan Singh ecfaac2dc7 fix(cli): prevent duplicate SessionStart systemMessage render (#25827)
Co-authored-by: Jacob Richman <jacob314@gmail.com>
2026-05-11 16:44:04 +00:00
Daniel Finimundi 7cd228f5af fix(cli): allow installing extensions from ssh repo (#26274)
Signed-off-by: Daniel Finimundi <danielrf@motorola.com>
Co-authored-by: Dev Randalpura <devrandalpura@google.com>
2026-05-11 15:57:52 +00:00
joshualitt 8a3fde4c33 fix(context): Change snapshotter model config. (#26745) 2026-05-11 15:06:55 +00:00
joshualitt 1a894c18ea feat(context): Improvements to the snapshotter. (#26655) 2026-05-08 23:54:44 +00:00
Adam Weidman 54f1e8c6d7 feat(core): add RemoteSubagentProtocol behind AgentProtocol (#25303) 2026-05-08 22:48:17 +00:00
krishdef7 f51391a0f2 fix(mcp): treat GET 404 as 405 in StreamableHTTPClientTransport (#24847)
Co-authored-by: Coco Sheng <cocosheng@google.com>
Co-authored-by: Spencer <spencertang@google.com>
Co-authored-by: Tommaso Sciortino <sciortino@gmail.com>
2026-05-08 22:16:08 +00:00
Sri Pasumarthi 1238dcfe91 feat(acp/core): prefix tool call IDs with tool names to support tool rendering in ACP compliant IDEs. (#26676) 2026-05-08 21:21:54 +00:00
Coco Sheng 90e7155971 ci: implement codebase-aware effort level triage (#26666) 2026-05-08 20:48:54 +00:00
JAYADITYA 9d0860bd0f fix(cli): remove noisy theme registration logs from terminal (#25858)
Co-authored-by: Jack Wotherspoon <jackwoth@google.com>
2026-05-08 19:59:33 +00:00
Adam Weidman 014bfeb89b feat(core): add LocalSubagentProtocol behind AgentProtocol (#25302) 2026-05-08 19:28:16 +00:00
Aishanee Shah 5890f50496 fix(core): resolve parallel tool call streaming ID collision (#26646) 2026-05-08 19:14:23 +00:00
Daniel Weis 6b9b778d82 fix: resolve "function response turn must come immediately after function call" error (#26691)
Co-authored-by: Tommaso Sciortino <sciortino@gmail.com>
2026-05-08 19:01:24 +00:00
Aishanee Shah f86e0ee418 fix(core): throw explicit error on dropped tool responses (#26668) 2026-05-08 18:36:39 +00:00
231 changed files with 10703 additions and 1314 deletions
+4 -1
View File
@@ -5,7 +5,10 @@
"autoMemory": true,
"memoryManager": true,
"topicUpdateNarration": true,
"voiceMode": true
"voiceMode": true,
"adk": {
"agentSessionNoninteractiveEnabled": true
}
},
"general": {
"devtools": true
+196
View File
@@ -0,0 +1,196 @@
/**
* @license
* Copyright 2026 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
module.exports = async ({ github, context, core }) => {
const rawLabels = process.env.LABELS_OUTPUT;
core.info(`Raw labels JSON: ${rawLabels}`);
let parsedLabels;
try {
// First, try to parse the raw output as JSON.
parsedLabels = JSON.parse(rawLabels);
} catch (jsonError) {
// If that fails, check for a markdown code block.
core.warning(
`Direct JSON parsing failed: ${jsonError.message}. Trying to extract from a markdown block.`,
);
const jsonMatch = rawLabels.match(/```json\s*([\s\S]*?)\s*```/);
if (jsonMatch && jsonMatch[1]) {
try {
parsedLabels = JSON.parse(jsonMatch[1].trim());
} catch (markdownError) {
core.setFailed(
`Failed to parse JSON even after extracting from markdown block: ${markdownError.message}\nRaw output: ${rawLabels}`,
);
return;
}
} else {
// If no markdown block, try to find a raw JSON array in the output.
// The CLI may include debug/log lines (e.g. telemetry init, YOLO mode)
// before the actual JSON response.
const jsonArrayMatch = rawLabels.match(
/\[\s*\{\s*"issue_number"[\s\S]*\}\s*\]/,
);
if (jsonArrayMatch) {
try {
parsedLabels = JSON.parse(jsonArrayMatch[0]);
} catch (extractError) {
// It's possible the regex matched from a `[STARTUP]` log all the way to the end
// of the JSON array. We need to be more aggressive and find the FIRST `[ { "issue_number"`
core.warning(
`Strict array match failed: ${extractError.message}. Attempting to clean leading noisy brackets.`,
);
const fallbackMatch = rawLabels.match(
/(\[\s*\{\s*"issue_number"[\s\S]*)/,
);
if (fallbackMatch) {
try {
// We might have grabbed trailing noise too, so we find the last closing bracket
const cleaned = fallbackMatch[0].substring(
0,
fallbackMatch[0].lastIndexOf(']') + 1,
);
parsedLabels = JSON.parse(cleaned);
} catch (fallbackError) {
core.setFailed(
`Found JSON-like content but failed to parse: ${fallbackError.message}\nRaw output: ${rawLabels}`,
);
return;
}
} else {
core.setFailed(
`Found JSON-like content but failed to parse: ${extractError.message}\nRaw output: ${rawLabels}`,
);
return;
}
}
} else {
core.setFailed(
`Output is not valid JSON and does not contain extractable JSON.\nRaw output: ${rawLabels}`,
);
return;
}
}
}
core.info(`Parsed labels JSON: ${JSON.stringify(parsedLabels)}`);
for (const entry of parsedLabels) {
const issueNumber = entry.issue_number;
if (!issueNumber) {
core.info(
`Skipping entry with no issue number: ${JSON.stringify(entry)}`,
);
continue;
}
let labelsToAdd = entry.labels_to_add || [];
let labelsToRemove = entry.labels_to_remove || [];
labelsToRemove.push('status/need-triage');
if (labelsToAdd.includes('status/manual-triage')) {
// If the AI flagged it for manual triage, remove bot-triaged if it exists
labelsToRemove.push('status/bot-triaged');
// Ensure we don't accidentally try to add bot-triaged if the AI returned it
labelsToAdd = labelsToAdd.filter((l) => l !== 'status/bot-triaged');
} else {
// Standard successful bot triage
labelsToAdd.push('status/bot-triaged');
}
// Deduplicate arrays
labelsToAdd = [...new Set(labelsToAdd)];
labelsToRemove = [...new Set(labelsToRemove)];
// Enforce mutually exclusive area labels
const areaLabelsToAdd = labelsToAdd.filter((l) => l.startsWith('area/'));
if (areaLabelsToAdd.length > 1) {
core.warning(
`Issue #${issueNumber} has multiple area labels to add: ${areaLabelsToAdd.join(', ')}. Keeping only the first one.`,
);
const firstArea = areaLabelsToAdd[0];
labelsToAdd = labelsToAdd.filter(
(l) => !l.startsWith('area/') || l === firstArea,
);
}
// Enforce mutually exclusive priority labels
const priorityLabelsToAdd = labelsToAdd.filter((l) =>
l.startsWith('priority/'),
);
if (priorityLabelsToAdd.length > 1) {
core.warning(
`Issue #${issueNumber} has multiple priority labels to add: ${priorityLabelsToAdd.join(', ')}. Keeping only the first one.`,
);
const firstPriority = priorityLabelsToAdd[0];
labelsToAdd = labelsToAdd.filter(
(l) => !l.startsWith('priority/') || l === firstPriority,
);
}
if (labelsToAdd.length > 0) {
await github.rest.issues.addLabels({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issueNumber,
labels: labelsToAdd,
});
const explanation = entry.explanation ? ` - ${entry.explanation}` : '';
core.info(
`Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}${explanation}`,
);
}
if (labelsToRemove.length > 0) {
for (const label of labelsToRemove) {
try {
await github.rest.issues.removeLabel({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issueNumber,
name: label,
});
} catch (e) {
if (e.status !== 404) {
core.warning(
`Failed to remove label ${label} from #${issueNumber}: ${e.message}`,
);
}
}
}
core.info(
`Successfully removed labels for #${issueNumber}: ${labelsToRemove.join(', ')}`,
);
}
if (entry.explanation || entry.effort_analysis) {
let commentBody = '';
if (entry.explanation) {
commentBody += entry.explanation;
}
if (entry.effort_analysis) {
if (commentBody) commentBody += '\n\n';
commentBody += `**Effort Analysis:**\n${entry.effort_analysis}`;
}
await github.rest.issues.createComment({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issueNumber,
body: commentBody,
});
}
if (
(!entry.labels_to_add || entry.labels_to_add.length === 0) &&
(!entry.labels_to_remove || entry.labels_to_remove.length === 0)
) {
core.info(
`No labels to add or remove for #${issueNumber}, leaving as is`,
);
}
}
};
+50
View File
@@ -0,0 +1,50 @@
/**
* @license
* Copyright 2026 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
const fs = require('node:fs');
module.exports = async ({ github, context, core }) => {
let issuesToCleanup = [];
try {
const fileContent = fs.readFileSync('issues_to_cleanup.json', 'utf8');
issuesToCleanup = JSON.parse(fileContent);
} catch (error) {
if (error.code === 'ENOENT') {
core.info('No issues found to clean up.');
return;
}
core.setFailed(`Failed to read issues_to_cleanup.json: ${error.message}`);
return;
}
for (const issue of issuesToCleanup) {
try {
await github.rest.issues.removeLabel({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issue.number,
name: 'status/need-triage',
});
core.info(
`Successfully removed status/need-triage from #${issue.number}`,
);
} catch (error) {
if (error.status === 404) {
core.info(
`Label status/need-triage not found on #${issue.number}, skipping.`,
);
} else {
core.warning(
`Failed to remove label from #${issue.number}: ${error.message}`,
);
}
}
}
core.info(
`Cleaned up status/need-triage from ${issuesToCleanup.length} issues.`,
);
};
@@ -0,0 +1,60 @@
/**
* @license
* Copyright 2026 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
const fs = require('node:fs');
module.exports = async ({ github, context, core }) => {
core.info('Fetching open issues to check for conflicting labels...');
const issues = await github.paginate(github.rest.issues.listForRepo, {
owner: context.repo.owner,
repo: context.repo.repo,
state: 'open',
per_page: 100,
});
const conflictingLabelIssues = [];
for (const issue of issues) {
if (issue.pull_request) continue;
const areaLabels = issue.labels
.filter((l) => l.name && l.name.startsWith('area/'))
.map((l) => l.name);
const priorityLabels = issue.labels
.filter((l) => l.name && l.name.startsWith('priority/'))
.map((l) => l.name);
if (areaLabels.length > 1 || priorityLabels.length > 1) {
let message = `Issue #${issue.number} has conflicting labels:`;
if (areaLabels.length > 1)
message += ` multiple areas (${areaLabels.join(', ')}).`;
if (priorityLabels.length > 1)
message += ` multiple priorities (${priorityLabels.join(', ')}).`;
core.info(message);
conflictingLabelIssues.push({
number: issue.number,
title: issue.title,
body: issue.body || '',
});
}
}
// Limit to 50 to avoid overwhelming the AI in a single run
const issuesToProcess = conflictingLabelIssues.slice(0, 50);
fs.writeFileSync(
'conflicting_labels_issues.json',
JSON.stringify(issuesToProcess, null, 2),
);
core.info(
`Found ${conflictingLabelIssues.length} issues with conflicting labels. Wrote ${issuesToProcess.length} to conflicting_labels_issues.json`,
);
};
+99
View File
@@ -0,0 +1,99 @@
/**
* @license
* Copyright 2026 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
const fs = require('node:fs');
module.exports = async ({ github, context, core }) => {
const query = `
query($owner: String!, $repo: String!) {
repository(owner: $owner, name: $repo) {
issues(first: 50, states: OPEN, orderBy: {field: UPDATED_AT, direction: DESC}) {
nodes {
id
number
title
body
issueType {
name
}
labels(first: 20) {
nodes {
name
}
}
}
}
}
}
`;
try {
const result = await github.graphql(query, {
owner: context.repo.owner,
repo: context.repo.repo,
});
const issues = result.repository.issues.nodes;
const issuesNeedingAnalysis = [];
let syncedCount = 0;
for (const issue of issues) {
if (issue.issueType === null) {
const labelNames = issue.labels.nodes.map((l) => l.name);
const hasBug = labelNames.includes('kind/bug');
const hasFeature =
labelNames.includes('kind/feature') ||
labelNames.includes('kind/enhancement');
let issueTypeId = null;
if (hasBug) {
issueTypeId = 'IT_kwDOCaSVvs4BR7vP'; // Bug
} else if (hasFeature) {
issueTypeId = 'IT_kwDOCaSVvs4BR7vQ'; // Feature
}
if (issueTypeId) {
await github.graphql(
`
mutation($issueId: ID!, $issueTypeId: ID!) {
updateIssue(input: {id: $issueId, issueTypeId: $issueTypeId}) {
issue {
id
}
}
}
`,
{
issueId: issue.id,
issueTypeId: issueTypeId,
},
);
core.info(`Successfully synced Issue Type for #${issue.number}`);
syncedCount++;
} else {
// Needs analysis to determine kind/type
issuesNeedingAnalysis.push({
number: issue.number,
title: issue.title,
body: issue.body,
});
}
}
}
// Write issues needing analysis to a file so the AI can process them
fs.writeFileSync(
'no_type_issues.json',
JSON.stringify(issuesNeedingAnalysis),
);
core.info(`Synced ${syncedCount} issues from labels.`);
core.info(
`Found ${issuesNeedingAnalysis.length} issues missing both type and kind label to be analyzed.`,
);
} catch (error) {
core.setFailed(`Failed to sync issue types: ${error.message}`);
}
};
@@ -30,6 +30,7 @@ jobs:
uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
with:
ref: '${{ inputs.ref || github.ref }}'
persist-credentials: false
- name: 'Set up Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
+4
View File
@@ -148,6 +148,7 @@ jobs:
with:
ref: '${{ needs.parse_run_context.outputs.sha }}'
repository: '${{ needs.parse_run_context.outputs.repository }}'
persist-credentials: false
- name: 'Set up Node.js ${{ matrix.node-version }}'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -193,6 +194,7 @@ jobs:
with:
ref: '${{ needs.parse_run_context.outputs.sha }}'
repository: '${{ needs.parse_run_context.outputs.repository }}'
persist-credentials: false
- name: 'Set up Node.js 20.x'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -233,6 +235,7 @@ jobs:
with:
ref: '${{ needs.parse_run_context.outputs.sha }}'
repository: '${{ needs.parse_run_context.outputs.repository }}'
persist-credentials: false
- name: 'Set up Node.js 20.x'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -314,6 +317,7 @@ jobs:
with:
ref: '${{ needs.parse_run_context.outputs.sha }}'
repository: '${{ needs.parse_run_context.outputs.repository }}'
persist-credentials: false
fetch-depth: 0
- name: 'Set up Node.js 20.x'
+10
View File
@@ -57,6 +57,7 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
ref: '${{ github.event.inputs.branch_ref || github.ref }}'
fetch-depth: 0
@@ -130,6 +131,8 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Link Checker'
uses: 'lycheeverse/lychee-action@885c65f3dc543b57c898c8099f4e08c8afd178a2' # ratchet: lycheeverse/lychee-action@v2.6.1
with:
@@ -157,6 +160,8 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Set up Node.js ${{ matrix.node-version }}'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -252,6 +257,8 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Set up Node.js ${{ matrix.node-version }}'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -339,6 +346,7 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
ref: '${{ github.event.inputs.branch_ref || github.ref }}'
- name: 'Initialize CodeQL'
@@ -363,6 +371,7 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
ref: '${{ github.event.inputs.branch_ref || github.ref }}'
fetch-depth: 1
@@ -390,6 +399,7 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
ref: '${{ github.event.inputs.branch_ref || github.ref }}'
- name: 'Set up Node.js 20.x'
+3
View File
@@ -43,6 +43,7 @@ jobs:
with:
ref: '${{ github.event.pull_request.head.sha }}'
repository: '${{ github.repository }}'
persist-credentials: false
- name: 'Set up Node.js ${{ matrix.node-version }}'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -86,6 +87,7 @@ jobs:
with:
ref: '${{ github.event.pull_request.head.sha }}'
repository: '${{ github.repository }}'
persist-credentials: false
- name: 'Set up Node.js 20.x'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -125,6 +127,7 @@ jobs:
with:
ref: '${{ github.event.pull_request.head.sha }}'
repository: '${{ github.repository }}'
persist-credentials: false
- name: 'Set up Node.js 20.x'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
+1
View File
@@ -19,6 +19,7 @@ jobs:
with:
fetch-depth: 0
ref: 'main'
persist-credentials: false
- name: 'Set up Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020'
+2
View File
@@ -24,6 +24,8 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Setup Pages'
uses: 'actions/configure-pages@983d7736d9b0ae728b81ab479565c72886d7745b' # ratchet:actions/configure-pages@v5
+2
View File
@@ -38,6 +38,7 @@ jobs:
with:
# Check out the trusted code from main for detection
fetch-depth: 0
persist-credentials: false
- name: 'Detect Steering Changes'
id: 'detect'
@@ -102,6 +103,7 @@ jobs:
# This only runs AFTER manual approval
ref: '${{ github.event.pull_request.head.sha }}'
fetch-depth: 0
persist-credentials: false
- name: 'Remove Approval Notification'
# Run even if other steps fail, to ensure we clean up the "Action Required" message
+4
View File
@@ -46,6 +46,8 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Set up Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -105,6 +107,8 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Download Logs'
uses: 'actions/download-artifact@cc203385981b70ca67e1cc392babf9cc229d5806' # ratchet:actions/download-artifact@v4
@@ -48,6 +48,8 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Log in to GitHub Container Registry'
uses: 'docker/login-action@184bdaa0721073962dff0199f1fb9940f07167d1' # ratchet:docker/login-action@v3
@@ -90,6 +90,8 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Generate GitHub App Token'
id: 'generate_token'
@@ -23,6 +23,7 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
fetch-depth: 0
- name: 'Setup Node.js'
@@ -33,6 +33,8 @@ jobs:
- name: 'Checkout repository'
uses: 'actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683' # ratchet:actions/checkout@v4
with:
persist-credentials: false
- name: 'Lifecycle Management'
uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
@@ -28,6 +28,8 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Log in to GitHub Container Registry'
uses: 'docker/login-action@184bdaa0721073962dff0199f1fb9940f07167d1' # ratchet:docker/login-action@v3
@@ -23,13 +23,15 @@ permissions:
jobs:
triage-issues:
timeout-minutes: 10
timeout-minutes: 60
if: |-
${{ github.repository == 'google-gemini/gemini-cli' }}
runs-on: 'ubuntu-latest'
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Generate GitHub App Token'
id: 'generate_token'
@@ -51,6 +53,26 @@ jobs:
echo "has_issues=true" >> "${GITHUB_OUTPUT}"
echo "✅ Found issue #${{ github.event.issue.number }} from event to triage! 🎯"
- name: 'Sync Issue Types'
if: |-
${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
with:
github-token: '${{ steps.generate_token.outputs.token }}'
script: |-
const syncIssueTypes = require('./.github/scripts/sync-issue-types.cjs');
await syncIssueTypes({ github, context, core });
- name: 'Find Issues with Conflicting Labels'
if: |-
${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
with:
github-token: '${{ steps.generate_token.outputs.token }}'
script: |-
const findConflictingLabels = require('./.github/scripts/find-conflicting-labels.cjs');
await findConflictingLabels({ github, context, core });
- name: 'Find untriaged issues'
if: |-
${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
@@ -63,26 +85,55 @@ jobs:
echo '🔍 Finding issues missing area labels...'
gh issue list --repo "${GITHUB_REPOSITORY}" \
--search 'is:open is:issue -label:status/bot-triaged -label:area/core -label:area/agent -label:area/enterprise -label:area/non-interactive -label:area/security -label:area/platform -label:area/extensions -label:area/documentation -label:area/unknown' --limit 100 --json number,title,body > no_area_issues.json
--search 'is:open is:issue -label:status/bot-triaged -label:area/core -label:area/agent -label:area/enterprise -label:area/non-interactive -label:area/security -label:area/platform -label:area/extensions -label:area/documentation -label:area/unknown' --limit 50 --json number,title,body > no_area_issues.json
echo '🔍 Finding issues missing kind labels...'
gh issue list --repo "${GITHUB_REPOSITORY}" \
--search 'is:open is:issue -label:status/bot-triaged -label:kind/bug -label:kind/enhancement -label:kind/customer-issue -label:kind/question' --limit 100 --json number,title,body > no_kind_issues.json
--search 'is:open is:issue -label:status/bot-triaged -label:kind/bug -label:kind/enhancement -label:kind/customer-issue -label:kind/question' --limit 50 --json number,title,body > no_kind_issues.json
echo '🏷️ Finding issues missing priority labels...'
gh issue list --repo "${GITHUB_REPOSITORY}" \
--search 'is:open is:issue -label:status/bot-triaged -label:priority/p0 -label:priority/p1 -label:priority/p2 -label:priority/p3 -label:priority/unknown' --limit 100 --json number,title,body > no_priority_issues.json
--search 'is:open is:issue -label:priority/p0 -label:priority/p1 -label:priority/p2 -label:priority/p3 -label:priority/unknown' --limit 50 --json number,title,body > no_priority_issues.json
echo '🔄 Merging and deduplicating issues...'
jq -c -s 'add | unique_by(.number)' no_area_issues.json no_kind_issues.json no_priority_issues.json > issues_to_triage.json
echo '📏 Finding issues missing effort labels...'
gh issue list --repo "${GITHUB_REPOSITORY}" \
--search 'is:open is:issue -label:effort/small -label:effort/medium -label:effort/large label:area/core,area/extensions,area/site,area/non-interactive' --limit 5 --json number,title,body > no_effort_issues.json
ISSUE_COUNT="$(jq 'length' issues_to_triage.json)"
if [ "$ISSUE_COUNT" -gt 0 ]; then
echo '🔄 Merging and deduplicating standard triage issues...'
if [ ! -f conflicting_labels_issues.json ]; then echo "[]" > conflicting_labels_issues.json; fi
jq -c -s 'add | unique_by(.number)' no_area_issues.json no_kind_issues.json no_priority_issues.json conflicting_labels_issues.json > standard_issues_to_triage.json
echo '📏 Deduplicating effort issues...'
jq -c -s 'add | unique_by(.number)' no_effort_issues.json > effort_issues_to_triage.json
STANDARD_COUNT="$(jq 'length' standard_issues_to_triage.json)"
EFFORT_COUNT="$(jq 'length' effort_issues_to_triage.json)"
if [ "$STANDARD_COUNT" -gt 0 ] || [ "$EFFORT_COUNT" -gt 0 ]; then
echo "has_issues=true" >> "${GITHUB_OUTPUT}"
echo "has_standard_issues=$([ "$STANDARD_COUNT" -gt 0 ] && echo 'true' || echo 'false')" >> "${GITHUB_OUTPUT}"
echo "has_effort_issues=$([ "$EFFORT_COUNT" -gt 0 ] && echo 'true' || echo 'false')" >> "${GITHUB_OUTPUT}"
else
echo "has_issues=false" >> "${GITHUB_OUTPUT}"
echo "has_standard_issues=false" >> "${GITHUB_OUTPUT}"
echo "has_effort_issues=false" >> "${GITHUB_OUTPUT}"
fi
echo "✅ Found ${ISSUE_COUNT} unique issues to triage! 🎯"
echo "✅ Found ${STANDARD_COUNT} standard issues and ${EFFORT_COUNT} effort issues to triage! 🎯"
- name: 'Create Gemini CLI Experiments Override'
if: |-
steps.get_issue_from_event.outputs.has_issues == 'true' || steps.find_issues.outputs.has_issues == 'true'
run: |
cat << 'EOF' > gemini_exp.json
{
"flags": [
{
"flagId": 45750526,
"boolValue": false
}
],
"experimentIds": []
}
EOF
- name: 'Get Repository Labels'
id: 'get_labels'
@@ -99,16 +150,18 @@ jobs:
core.info(`Found ${labelNames.length} labels: ${labelNames.join(', ')}`);
return labelNames;
- name: 'Run Gemini Issue Analysis'
- name: 'Run Standard Triage Analysis'
if: |-
steps.get_issue_from_event.outputs.has_issues == 'true' || steps.find_issues.outputs.has_issues == 'true'
steps.get_issue_from_event.outputs.has_issues == 'true' || steps.find_issues.outputs.has_standard_issues == 'true'
uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0
id: 'gemini_issue_analysis'
id: 'gemini_standard_issue_analysis'
env:
GITHUB_TOKEN: '' # Do not pass any auth token here since this runs on untrusted inputs
REPOSITORY: '${{ github.repository }}'
AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
GEMINI_CLI_TRUST_WORKSPACE: 'true'
GEMINI_EXP: 'gemini_exp.json'
GEMINI_STRICT_TELEMETRY_LIMITS: 'true'
with:
gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
@@ -139,13 +192,15 @@ jobs:
## Steps
1. You are only able to use the echo and read_file commands. Review the available labels in the environment variable: "${AVAILABLE_LABELS}".
2. Use the read_file tool to read the file "issues_to_triage.json" which contains the JSON array of issues to triage.
2. Use the read_file tool to read the file "standard_issues_to_triage.json" which contains the JSON array of issues to triage.
3. Review the issue title, body and any comments provided in the JSON file.
4. Identify the most relevant labels from the existing labels, specifically focusing on area/*, kind/* and priority/*.
4. Identify the most relevant labels from the existing labels, specifically focusing on area/*, kind/*, and priority/*.
5. Label Policy:
- If the issue already has a kind/ label, do not change it.
- If the issue already has a priority/ label, do not change it.
- If the issue already has an area/ label, do not change it.
- If the issue has exactly ONE priority/ label, do not change it.
- If the issue is missing a priority/ label, OR if the issue currently has MULTIPLE priority/ labels, you must evaluate the issue's impact to determine exactly ONE priority level (priority/p0, priority/p1, priority/p2, priority/p3, or priority/unknown) based the guidelines. If you are fixing an issue with multiple priority/ labels, put the correct one in `labels_to_add` and put all the incorrect ones in `labels_to_remove`.
- If the issue has exactly ONE area/ label, do not change it.
- If the issue is missing an area/ label, OR if the issue currently has MULTIPLE area/ labels, select exactly ONE area/ label that best fits the issue. Issues MUST NOT have multiple area/ labels. If you are fixing an issue with multiple area/ labels, put the correct one in `labels_to_add` and put all the incorrect ones in `labels_to_remove`.
- If any of these are missing, select exactly ONE appropriate label for the missing category.
6. Identify other applicable labels based on the issue content, such as status/*, help wanted, good first issue, etc.
7. Give me a single short explanation about why you are selecting each label in the process.
@@ -176,11 +231,121 @@ jobs:
- Do not add comments or modify the issue content.
- Do not remove the following labels maintainer, help wanted or good first issue.
- Triage only the current issue.
- Identify only one area/ label.
- Identify exactly ONE area/ label. Do NOT assign multiple area/ labels to a single issue.
- Identify only one kind/ label (Do not apply kind/duplicate or kind/parent-issue)
- Identify only one priority/ label.
- Identify exactly ONE priority/ label. Do NOT assign multiple priority/ labels to a single issue.
- Once you categorize the issue if it needs information bump down the priority by 1 eg.. a p0 would become a p1 a p1 would become a p2. P2 and P3 can stay as is in this scenario.
Categorization Guidelines (Priority):
P0 - Urgent Blocking Issues:
- Definition: Critical failures breaking core functionality for a large portion of users. Examples: CLI fails to launch globally, core commands (gemini run) crash on valid input, unhandled promise rejections on boot, critical security vulnerability.
- Note: You must apply status/manual-triage instead of priority/p0.
P1 - Critical but Workable:
- Definition: Severe issues without a reasonable workaround, significantly degrading the developer experience but not globally blocking. Examples: Specific tools failing consistently (e.g., `web_search` returns 500s), persistent PTY streaming hangs, memory leaks leading to OOM after short use.
P2 - Significant Issues:
- Definition: Affect some workflows but a clear workaround exists, or non-critical bugs. Examples: Theme flickering, confusing error messages, minor UI misalignment, failing to read deeply nested config files correctly.
P3 - Minor/Enhancements:
- Definition: Trivial bugs, typos, documentation requests, or feature requests.
Categorization Guidelines (Kind):
kind/bug: The issue is describing an unexpected behavior or failure in the application.
kind/enhancement: The issue is describing a feature request or an improvement to an existing feature.
kind/question: The issue is asking a question about how to use the CLI or about a specific feature.
Categorization Guidelines (Area):
area/agent: The "brain" of the CLI. Core agent logic, model quality, tool/function calling, memory, web search, generated code quality, sub-agents.
area/core: The fundamental CLI app. UI/UX, installation, OS compatibility, performance, command parsing, theming, flickering.
area/documentation: Website docs, READMEs, inline help text.
area/enterprise: Telemetry, Policy, Quota / Licensing
area/extensions: Gemini CLI extensions capability
area/non-interactive: GitHub Actions, SDK, 3P Integrations, Shell Scripting, Command line automation
area/platform: Platform specific behavior
area/security: Authentication, authorization, privacy, data leaks, credential storage.
- name: 'Stop Telemetry Collector'
if: |-
steps.find_issues.outputs.has_effort_issues == 'true'
run: 'docker rm -f gemini-telemetry-collector || true'
- name: 'Run Effort Triage Analysis'
if: |-
steps.find_issues.outputs.has_effort_issues == 'true'
uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0
id: 'gemini_effort_issue_analysis'
env:
GITHUB_TOKEN: '' # Do not pass any auth token here since this runs on untrusted inputs
REPOSITORY: '${{ github.repository }}'
AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
GEMINI_CLI_TRUST_WORKSPACE: 'true'
GEMINI_EXP: 'gemini_exp.json'
GEMINI_STRICT_TELEMETRY_LIMITS: 'true'
with:
gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
gcp_service_account: '${{ vars.SERVICE_ACCOUNT_EMAIL }}'
gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
use_vertex_ai: '${{ vars.GOOGLE_GENAI_USE_VERTEXAI }}'
use_gemini_code_assist: '${{ vars.GOOGLE_GENAI_USE_GCA }}'
settings: |-
{
"maxSessionTurns": 25,
"coreTools": [
"run_shell_command(echo)",
"grep_search",
"glob",
"read_file"
],
"telemetry": {
"enabled": true,
"target": "gcp"
}
}
prompt: |-
## Role
You are an expert software architect. Analyze the provided GitHub issues and assign the correct `effort/*` label based on the codebase complexity.
## Steps
1. Use the read_file tool to read "effort_issues_to_triage.json".
2. For each issue in the array:
- You must evaluate the architectural complexity to determine the effort level. You MUST NOT guess the root cause. You MUST actively use your codebase search tools (grep_search and glob) to search for keywords from the issue and explore the codebase. You must identify the specific files and components involved before deciding the effort.
3. Output a JSON array of objects, each containing the issue number and the effort label to add, along with an explanation and an effort_analysis field. This effort_analysis must be highly detailed, technical, and empirical. It MUST NOT contain vague guesses (e.g., avoid words like "likely points to" or "possibly"). You must explicitly cite the specific file paths and architectural mechanisms you discovered using your search tools, explain the root cause, and then explicitly state how that complexity maps to the chosen effort level guidelines. For example:
```
[
{
"issue_number": 123,
"labels_to_add": ["effort/small"],
"explanation": "This is a simple logic fix.",
"effort_analysis": "The `vscode-ide-companion` extension indiscriminately tracks active text editors via `vscode.window.onDidChangeActiveTextEditor` in `open-files-manager.ts`. When a user opens `.vscode/settings.json`, its content is sent to the CLI's context. The fix is highly localized to the VS Code companion extension's event listener. It involves adding a simple conditional check to exclude specific configuration files from the active editor tracking logic, which is a trivial logic adjustment with a clear root cause."
}
]
```
## Guidelines
- Output only valid JSON format
- Do not include any explanation or additional text, just the JSON
- Triage only the current issue.
Categorization Guidelines (Effort):
effort/small (1 day or less):
- Trivial Logic & Config: Schema updates (Zod), feature flag toggles, adding missing fields to package.json or settings.json.
- UI/Aesthetic Adjustments: Fixing minor layout bugs in Ink components (e.g., adding flexShrink, correcting padding in a single Box), text color changes.
- Documentation & Strings: Typos, log message updates, CLI argument descriptions.
- Localized Bug Fixes: Single-file logic errors, straightforward promise rejections (e.g., wrapping a known failure in a try/catch), simple regex or string parsing fixes.
effort/medium (2-3 days):
- React/Ink State Management: Debugging useState/useEffect/useReducer bugs, component lifecycle issues (memory leaks in the UI), terminal redraw flickering, or state synchronization between the CLI's internal input buffer and the interactive React components.
- Asynchronous Flow & Integration: Resolving complex Promise chains, ERR_STREAM_PREMATURE_CLOSE, debugging IDE companion extensions (VS Code, Android Studio) or resolving hanging HTTP requests/IPC between the CLI and external plugins, timeouts in non-interactive/ACP modes.
- Tooling & Output Parsers: Modifying how tools parse streaming stdout/stderr buffers, adding new built-in tools that don't require native bindings.
- Cross-Component Refactors: Changes that span across packages/cli and packages/core to pass new data models or telemetry state.
effort/large (3+ days):
- Platform-Specific Complexities (PTY/Signals): Any issue involving node-pty, child_process.spawn, OS-level shell behavior (Windows vs Linux vs macOS), pseudo-terminal exhaustion (ENXIO), raw mode terminal desyncs, or POSIX signal forwarding (SIGINT/SIGTERM).
- Core Architecture & Protocols: Refactoring the Scheduler, Agent-to-Agent (A2A) protocol implementation, low-level MCP (Model Context Protocol) transport mechanisms.
- Performance & Memory: Diagnosing massive disk/memory leaks, severe boot time regressions, high-throughput streaming optimizations (e.g., voice streaming pipelines).
Note: Any bug that is described as intermittent, flickering, difficult to reproduce, platform-specific, or requiring cross-environment setups (e.g., involving the VS Code IDE companion, GCA plugin, or Android Studio) MUST NOT be rated as effort/small because of the increased overhead of testing and reproducing.
Categorization Guidelines (Priority):
P0 - Urgent Blocking Issues:
- DO NOT APPLY THIS LABEL AUTOMATICALLY. Use status/manual-triage instead.
@@ -218,85 +383,64 @@ jobs:
- This product is designed to use different models eg.. using pro, downgrading to flash etc.
- When users report that they dont expect the model to change those would be categorized as feature requests.
- name: 'Apply Labels to Issues'
- name: 'Apply Standard Labels to Issues'
if: |-
${{ steps.gemini_issue_analysis.outcome == 'success' &&
steps.gemini_issue_analysis.outputs.summary != '[]' }}
${{ steps.gemini_standard_issue_analysis.outcome == 'success' &&
steps.gemini_standard_issue_analysis.outputs.summary != '[]' &&
steps.gemini_standard_issue_analysis.outputs.summary != '' }}
env:
REPOSITORY: '${{ github.repository }}'
LABELS_OUTPUT: '${{ steps.gemini_issue_analysis.outputs.summary }}'
LABELS_OUTPUT: '${{ steps.gemini_standard_issue_analysis.outputs.summary }}'
uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
with:
github-token: '${{ steps.generate_token.outputs.token }}'
script: |-
const rawLabels = process.env.LABELS_OUTPUT;
core.info(`Raw labels JSON: ${rawLabels}`);
let parsedLabels;
try {
// First, try to parse the raw output as JSON.
parsedLabels = JSON.parse(rawLabels);
} catch (jsonError) {
// If that fails, check for a markdown code block.
core.warning(`Direct JSON parsing failed: ${jsonError.message}. Trying to extract from a markdown block.`);
const jsonMatch = rawLabels.match(/```json\s*([\s\S]*?)\s*```/);
if (jsonMatch && jsonMatch[1]) {
try {
parsedLabels = JSON.parse(jsonMatch[1].trim());
} catch (markdownError) {
core.setFailed(`Failed to parse JSON even after extracting from markdown block: ${markdownError.message}\nRaw output: ${rawLabels}`);
return;
}
} else {
// If no markdown block, try to find a raw JSON array in the output.
// The CLI may include debug/log lines (e.g. telemetry init, YOLO mode)
// before the actual JSON response.
const jsonArrayMatch = rawLabels.match(/(\[[\s\S]*\])/);
if (jsonArrayMatch) {
try {
parsedLabels = JSON.parse(jsonArrayMatch[0]);
} catch (extractError) {
core.setFailed(`Found JSON-like content but failed to parse: ${extractError.message}\nRaw output: ${rawLabels}`);
return;
}
} else {
core.setFailed(`Output is not valid JSON and does not contain extractable JSON.\nRaw output: ${rawLabels}`);
return;
}
}
}
core.info(`Parsed labels JSON: ${JSON.stringify(parsedLabels)}`);
const applyLabels = require('./.github/scripts/apply-issue-labels.cjs');
await applyLabels({ github, context, core });
for (const entry of parsedLabels) {
const issueNumber = entry.issue_number;
if (!issueNumber) {
core.info(`Skipping entry with no issue number: ${JSON.stringify(entry)}`);
continue;
}
- name: 'Apply Effort Labels to Issues'
if: |-
${{ steps.gemini_effort_issue_analysis.outcome == 'success' &&
steps.gemini_effort_issue_analysis.outputs.summary != '[]' &&
steps.gemini_effort_issue_analysis.outputs.summary != '' }}
env:
REPOSITORY: '${{ github.repository }}'
LABELS_OUTPUT: '${{ steps.gemini_effort_issue_analysis.outputs.summary }}'
uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
with:
github-token: '${{ steps.generate_token.outputs.token }}'
script: |-
const applyLabels = require('./.github/scripts/apply-issue-labels.cjs');
await applyLabels({ github, context, core });
const labelsToAdd = entry.labels_to_add || [];
labelsToAdd.push('status/bot-triaged');
- name: 'Sync Issue Types (Post-Analysis)'
if: |-
always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
with:
github-token: '${{ steps.generate_token.outputs.token }}'
script: |-
const syncIssueTypes = require('./.github/scripts/sync-issue-types.cjs');
await syncIssueTypes({ github, context, core });
if (labelsToAdd.length > 0) {
await github.rest.issues.addLabels({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issueNumber,
labels: labelsToAdd
});
const explanation = entry.explanation ? ` - ${entry.explanation}` : '';
core.info(`Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}${explanation}`);
}
- name: 'Find Triaged Issues to Clean Up'
if: |-
always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
env:
GITHUB_TOKEN: '${{ steps.generate_token.outputs.token }}'
GITHUB_REPOSITORY: '${{ github.repository }}'
run: |-
set -euo pipefail
echo '🧹 Finding issues that have both bot-triaged and need-triage labels...'
gh issue list --repo "${GITHUB_REPOSITORY}" \
--search 'is:open is:issue label:status/bot-triaged label:status/need-triage' --limit 50 --json number > issues_to_cleanup.json
if (entry.explanation) {
await github.rest.issues.createComment({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issueNumber,
body: entry.explanation,
});
}
if ((!entry.labels_to_add || entry.labels_to_add.length === 0) && (!entry.labels_to_remove || entry.labels_to_remove.length === 0)) {
core.info(`No labels to add or remove for #${issueNumber}, leaving as is`);
}
}
- name: 'Clean Up Triage Labels'
if: |-
always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
with:
github-token: '${{ steps.generate_token.outputs.token }}'
script: |-
const cleanupLabels = require('./.github/scripts/cleanup-triage-labels.cjs');
await cleanupLabels({ github, context, core });
@@ -21,6 +21,8 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Generate GitHub App Token'
id: 'generate_token'
@@ -19,6 +19,8 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
with:
persist-credentials: false
- name: 'Setup Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -41,6 +43,8 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
with:
persist-credentials: false
- name: 'Setup Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
+2
View File
@@ -17,6 +17,8 @@ jobs:
runs-on: 'ubuntu-latest'
steps:
- uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Link Checker'
id: 'lychee'
+2
View File
@@ -16,6 +16,8 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Set up Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
+2
View File
@@ -16,6 +16,8 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Set up Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -44,6 +44,7 @@ jobs:
with:
ref: '${{ github.ref }}'
fetch-depth: 0
persist-credentials: false
- name: 'Setup Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020'
+2
View File
@@ -65,11 +65,13 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
fetch-depth: 0
- name: 'Checkout Release Code'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ github.event.inputs.ref }}'
path: 'release'
fetch-depth: 0
+2
View File
@@ -50,11 +50,13 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
fetch-depth: 0
- name: 'Checkout Release Code'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ github.event.inputs.ref }}'
path: 'release'
fetch-depth: 0
+1
View File
@@ -31,6 +31,7 @@ jobs:
- name: 'Checkout repository'
uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
with:
persist-credentials: false
# The user-level skills need to be available to the workflow
fetch-depth: 0
ref: 'main'
@@ -17,6 +17,7 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
fetch-depth: 1
- name: 'Slash Command Dispatch'
@@ -54,6 +54,7 @@ jobs:
with:
ref: '${{ github.event.inputs.ref }}'
fetch-depth: 0
persist-credentials: false
- name: 'Setup Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -64,6 +64,7 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: "${{ github.event.inputs.workflow_ref || 'main' }}"
fetch-depth: 1
@@ -53,12 +53,14 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
fetch-depth: 0
fetch-tags: true
- name: 'Checkout Release Code'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ github.event.inputs.release_ref }}'
path: 'release'
fetch-depth: 0
+8
View File
@@ -55,6 +55,7 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
fetch-depth: 0
fetch-tags: true
@@ -171,11 +172,13 @@ jobs:
- name: 'Checkout Ref'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ github.event.inputs.ref }}'
- name: 'Checkout correct SHA'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ matrix.sha }}'
path: 'release'
fetch-depth: 0
@@ -216,11 +219,13 @@ jobs:
- name: 'Checkout Ref'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ github.event.inputs.ref }}'
- name: 'Checkout correct SHA'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ needs.calculate-versions.outputs.PREVIEW_SHA }}'
path: 'release'
fetch-depth: 0
@@ -288,11 +293,13 @@ jobs:
- name: 'Checkout Ref'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ github.event.inputs.ref }}'
- name: 'Checkout correct SHA'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ needs.calculate-versions.outputs.STABLE_SHA }}'
path: 'release'
fetch-depth: 0
@@ -360,6 +367,7 @@ jobs:
- name: 'Checkout Ref'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ github.event.inputs.ref }}'
- name: 'Setup Node.js'
+1
View File
@@ -52,6 +52,7 @@ jobs:
- name: 'Checkout repository'
uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v4
with:
persist-credentials: false
ref: '${{ github.event.inputs.ref }}'
fetch-depth: 0
+1
View File
@@ -26,6 +26,7 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ github.event.inputs.ref || github.sha }}'
fetch-depth: 0
- name: 'Push'
+1
View File
@@ -32,6 +32,7 @@ jobs:
with:
ref: '${{ github.event.inputs.ref || github.sha }}'
fetch-depth: 0
persist-credentials: false
- name: 'Install Dependencies'
run: 'npm ci'
- name: 'Build bundle'
+2
View File
@@ -34,6 +34,8 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
with:
persist-credentials: false
- name: 'Optimize Windows Performance'
if: "matrix.os == 'windows-latest'"
+2
View File
@@ -44,6 +44,8 @@ jobs:
shell: 'bash'
run: 'echo "${{ toJSON(vars) }}"'
- uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
- name: 'Verify release'
uses: './.github/actions/verify-release'
with:
+5 -1
View File
@@ -43,9 +43,13 @@
{
"type": "node",
"request": "launch",
"name": "Launch Program",
"name": "CLI: Run Current File",
"runtimeExecutable": "node",
"runtimeArgs": ["--import", "tsx"],
"skipFiles": ["<node_internals>/**"],
"program": "${file}",
"cwd": "${workspaceFolder}",
"console": "integratedTerminal",
"outFiles": ["${workspaceFolder}/**/*.js"]
},
{
+148 -59
View File
@@ -545,6 +545,24 @@ their corresponding top-level category object in your `settings.json` file.
"model": "gemini-3-flash-preview"
}
},
"gemini-3.1-pro-preview": {
"extends": "chat-base-3",
"modelConfig": {
"model": "gemini-3.1-pro-preview"
}
},
"gemini-3.1-pro-preview-customtools": {
"extends": "chat-base-3",
"modelConfig": {
"model": "gemini-3.1-pro-preview-customtools"
}
},
"gemini-3.1-flash-lite-preview": {
"extends": "chat-base-3",
"modelConfig": {
"model": "gemini-3.1-flash-lite-preview"
}
},
"gemini-2.5-pro": {
"extends": "chat-base-2.5",
"modelConfig": {
@@ -563,6 +581,18 @@ their corresponding top-level category object in your `settings.json` file.
"model": "gemini-2.5-flash-lite"
}
},
"gemini-3.1-flash-lite": {
"extends": "chat-base-3",
"modelConfig": {
"model": "gemini-3.1-flash-lite"
}
},
"gemini-3.5-flash": {
"extends": "chat-base-3",
"modelConfig": {
"model": "gemini-3.5-flash"
}
},
"gemma-4-31b-it": {
"extends": "chat-base-3",
"modelConfig": {
@@ -587,10 +617,16 @@ their corresponding top-level category object in your `settings.json` file.
"model": "gemini-3-flash-preview"
}
},
"gemini-3.5-flash-base": {
"extends": "base",
"modelConfig": {
"model": "gemini-3.5-flash"
}
},
"classifier": {
"extends": "base",
"modelConfig": {
"model": "gemini-2.5-flash-lite",
"model": "flash-lite",
"generateContentConfig": {
"maxOutputTokens": 1024,
"thinkingConfig": {
@@ -602,7 +638,7 @@ their corresponding top-level category object in your `settings.json` file.
"prompt-completion": {
"extends": "base",
"modelConfig": {
"model": "gemini-2.5-flash-lite",
"model": "flash-lite",
"generateContentConfig": {
"temperature": 0.3,
"maxOutputTokens": 16000,
@@ -615,7 +651,7 @@ their corresponding top-level category object in your `settings.json` file.
"fast-ack-helper": {
"extends": "base",
"modelConfig": {
"model": "gemini-2.5-flash-lite",
"model": "flash-lite",
"generateContentConfig": {
"temperature": 0.2,
"maxOutputTokens": 120,
@@ -628,7 +664,7 @@ their corresponding top-level category object in your `settings.json` file.
"edit-corrector": {
"extends": "base",
"modelConfig": {
"model": "gemini-2.5-flash-lite",
"model": "flash-lite",
"generateContentConfig": {
"thinkingConfig": {
"thinkingBudget": 0
@@ -639,7 +675,7 @@ their corresponding top-level category object in your `settings.json` file.
"summarizer-default": {
"extends": "base",
"modelConfig": {
"model": "gemini-2.5-flash-lite",
"model": "flash-lite",
"generateContentConfig": {
"maxOutputTokens": 2000
}
@@ -648,7 +684,7 @@ their corresponding top-level category object in your `settings.json` file.
"summarizer-shell": {
"extends": "base",
"modelConfig": {
"model": "gemini-2.5-flash-lite",
"model": "flash-lite",
"generateContentConfig": {
"maxOutputTokens": 2000
}
@@ -700,6 +736,19 @@ their corresponding top-level category object in your `settings.json` file.
"extends": "gemini-3-flash-base",
"modelConfig": {}
},
"context-snapshotter": {
"extends": "gemini-3-flash-base",
"modelConfig": {
"generateContentConfig": {
"thinkingConfig": {
"thinkingLevel": "HIGH"
},
"temperature": 1,
"topP": 0.95,
"topK": 64
}
}
},
"chat-compression-3-pro": {
"modelConfig": {
"model": "gemini-3-pro-preview"
@@ -712,7 +761,7 @@ their corresponding top-level category object in your `settings.json` file.
},
"chat-compression-3.1-flash-lite": {
"modelConfig": {
"model": "gemini-3.1-flash-lite-preview"
"model": "gemini-3.1-flash-lite"
}
},
"chat-compression-2.5-pro": {
@@ -766,10 +815,10 @@ their corresponding top-level category object in your `settings.json` file.
```json
{
"gemini-3.1-flash-lite-preview": {
"gemini-3.1-flash-lite": {
"tier": "flash-lite",
"family": "gemini-3",
"isPreview": true,
"isPreview": false,
"isVisible": true,
"features": {
"thinking": false,
@@ -816,6 +865,16 @@ their corresponding top-level category object in your `settings.json` file.
"multimodalToolUse": true
}
},
"gemini-3.5-flash": {
"tier": "flash",
"family": "gemini-3",
"isPreview": false,
"isVisible": true,
"features": {
"thinking": false,
"multimodalToolUse": true
}
},
"gemini-2.5-pro": {
"tier": "pro",
"family": "gemini-2.5",
@@ -869,9 +928,10 @@ their corresponding top-level category object in your `settings.json` file.
}
},
"auto": {
"displayName": "Auto",
"tier": "auto",
"isPreview": true,
"isVisible": false,
"isVisible": true,
"features": {
"thinking": true,
"multimodalToolUse": false
@@ -905,26 +965,16 @@ their corresponding top-level category object in your `settings.json` file.
}
},
"auto-gemini-3": {
"displayName": "Auto (Gemini 3)",
"tier": "auto",
"family": "gemini-3",
"isPreview": true,
"isVisible": true,
"dialogDescription": "Let Gemini CLI decide the best model for the task: gemini-3-pro, gemini-3-flash",
"features": {
"thinking": true,
"multimodalToolUse": false
}
"isVisible": false
},
"auto-gemini-2.5": {
"displayName": "Auto (Gemini 2.5)",
"tier": "auto",
"family": "gemini-2.5",
"isPreview": false,
"isVisible": true,
"dialogDescription": "Let Gemini CLI decide the best model for the task: gemini-2.5-pro, gemini-2.5-flash",
"features": {
"thinking": false,
"multimodalToolUse": false
}
"isVisible": false
}
}
```
@@ -977,37 +1027,50 @@ their corresponding top-level category object in your `settings.json` file.
"contexts": [
{
"condition": {
"hasAccessToPreview": false
"hasAccessToPreview": false,
"useGemini3_5Flash": true
},
"target": "gemini-3.5-flash"
},
{
"condition": {
"hasAccessToPreview": false,
"useGemini3_5Flash": false
},
"target": "gemini-2.5-flash"
}
]
},
"gemini-3-pro-preview": {
"default": "gemini-3-pro-preview",
"gemini-3.5-flash": {
"default": "gemini-3.5-flash",
"contexts": [
{
"condition": {
"useGemini3_5Flash": false,
"hasAccessToPreview": false
},
"target": "gemini-2.5-pro"
"target": "gemini-2.5-flash"
},
{
"condition": {
"useGemini3_1": true,
"useCustomTools": true
"useGemini3_5Flash": false
},
"target": "gemini-3.1-pro-preview-customtools"
},
{
"condition": {
"useGemini3_1": true
},
"target": "gemini-3.1-pro-preview"
"target": "gemini-3-flash-preview"
}
]
},
"auto-gemini-3": {
"gemini-2.5-flash": {
"default": "gemini-2.5-flash",
"contexts": [
{
"condition": {
"useGemini3_5Flash": true
},
"target": "gemini-3.5-flash"
}
]
},
"gemini-3-pro-preview": {
"default": "gemini-3-pro-preview",
"contexts": [
{
@@ -1079,23 +1142,18 @@ their corresponding top-level category object in your `settings.json` file.
}
]
},
"auto-gemini-2.5": {
"default": "gemini-2.5-pro"
},
"gemini-3.1-flash-lite-preview": {
"default": "gemini-3.1-flash-lite-preview",
"contexts": [
{
"condition": {
"useGemini3_1FlashLite": false
},
"target": "gemini-2.5-flash-lite"
}
]
"gemini-3.1-flash-lite": {
"default": "gemini-3.1-flash-lite"
},
"flash": {
"default": "gemini-3-flash-preview",
"contexts": [
{
"condition": {
"useGemini3_5Flash": true
},
"target": "gemini-3.5-flash"
},
{
"condition": {
"hasAccessToPreview": false
@@ -1105,15 +1163,34 @@ their corresponding top-level category object in your `settings.json` file.
]
},
"flash-lite": {
"default": "gemini-2.5-flash-lite",
"default": "gemini-3.1-flash-lite"
},
"auto-gemini-3": {
"default": "gemini-3-pro-preview",
"contexts": [
{
"condition": {
"useGemini3_1FlashLite": true
"hasAccessToPreview": false
},
"target": "gemini-3.1-flash-lite-preview"
"target": "gemini-2.5-pro"
},
{
"condition": {
"useGemini3_1": true,
"useCustomTools": true
},
"target": "gemini-3.1-pro-preview-customtools"
},
{
"condition": {
"useGemini3_1": true
},
"target": "gemini-3.1-pro-preview"
}
]
},
"auto-gemini-2.5": {
"default": "gemini-2.5-pro"
}
}
```
@@ -1132,15 +1209,21 @@ their corresponding top-level category object in your `settings.json` file.
"contexts": [
{
"condition": {
"requestedModels": ["auto-gemini-2.5", "gemini-2.5-pro"]
"useGemini3_5Flash": true
},
"target": "gemini-3.5-flash"
},
{
"condition": {
"hasAccessToPreview": false
},
"target": "gemini-2.5-flash"
},
{
"condition": {
"requestedModels": ["auto-gemini-3", "gemini-3-pro-preview"]
"requestedModels": ["gemini-2.5-pro", "auto-gemini-2.5"]
},
"target": "gemini-3-flash-preview"
"target": "gemini-2.5-flash"
}
]
},
@@ -1149,7 +1232,13 @@ their corresponding top-level category object in your `settings.json` file.
"contexts": [
{
"condition": {
"requestedModels": ["auto-gemini-2.5", "gemini-2.5-pro"]
"hasAccessToPreview": false
},
"target": "gemini-2.5-pro"
},
{
"condition": {
"requestedModels": ["gemini-2.5-pro", "auto-gemini-2.5"]
},
"target": "gemini-2.5-pro"
},
@@ -1320,7 +1409,7 @@ their corresponding top-level category object in your `settings.json` file.
],
"lite": [
{
"model": "gemini-2.5-flash-lite",
"model": "flash-lite",
"actions": {
"terminal": "silent",
"transient": "silent",
+5
View File
@@ -54,6 +54,11 @@ describe('interactive_commands', () => {
suiteName: 'default',
suiteType: 'behavioral',
name: 'should use non-interactive flags when scaffolding a new app',
params: {
settings: {
plan: false,
},
},
prompt: 'Create a new react application named my-app using vite.',
assert: async (rig, result) => {
const logs = rig.readToolLogs();
+114
View File
@@ -0,0 +1,114 @@
/**
* @license
* Copyright 2026 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
import { LlmRole, type BaseLlmClient } from '@google/gemini-cli-core';
export interface JudgeOptions {
/**
* The number of parallel generations to run for majority voting.
* Defaults to 1. Use 3 or 5 for self-consistency.
*/
selfConsistencyRuns?: number;
/**
* The model to use for judging. Defaults to gemini-3-flash-base.
*/
model?: string;
}
export interface JudgeResult {
verdict: boolean;
reasoning: string[];
votes: { yes: number; no: number; other: number };
}
/**
* A reusable LLM-as-a-judge utility for behavioral evaluations.
*/
export class LLMJudge {
constructor(private readonly llmClient: BaseLlmClient) {}
/**
* Asks the LLM a Yes/No question and returns a boolean verdict.
* If selfConsistencyRuns > 1, it runs in parallel and returns the majority vote.
*/
async judgeYesNo(
question: string,
options: JudgeOptions = {},
): Promise<JudgeResult> {
const runs = options.selfConsistencyRuns ?? 1;
const model = options.model ?? 'gemini-3-flash-base';
const systemPrompt = `You are a strict, impartial expert judge. Read the provided evidence and question carefully. You MUST answer the question with ONLY "YES" or "NO". Do not provide any conversational filler or explanation before your answer.`;
const generateCall = async (): Promise<string> => {
try {
const response = await this.llmClient.generateContent({
modelConfigKey: { model },
contents: [{ role: 'user', parts: [{ text: question }] }],
systemInstruction: {
role: 'system',
parts: [{ text: systemPrompt }],
},
promptId: 'llm-judge-eval',
role: LlmRole.UTILITY_TOOL,
abortSignal: new AbortController().signal,
});
const text =
response.candidates?.[0]?.content?.parts?.[0]?.text
?.trim()
?.toUpperCase() || 'ERROR';
return text;
} catch (e: any) {
return `ERROR: ${e.message}`;
}
};
const promises = Array.from({ length: runs }).map(() => generateCall());
const rawResults = await Promise.all(promises);
let yes = 0;
let no = 0;
let other = 0;
for (const res of rawResults) {
// Remove any punctuation the model might have appended
const cleanRes = res.toUpperCase().replace(/[^A-Z ]/g, '');
if (
cleanRes.includes('THE ANSWER IS YES') ||
cleanRes.includes('ANSWER IS YES') ||
cleanRes.endsWith('YES')
) {
yes++;
} else if (
cleanRes.includes('THE ANSWER IS NO') ||
cleanRes.includes('ANSWER IS NO') ||
cleanRes.endsWith('NO')
) {
no++;
} else if (cleanRes.trim() === 'YES') {
yes++;
} else if (cleanRes.trim() === 'NO') {
no++;
} else {
// Fallback: look for YES or NO as standalone words or at the end
const words = cleanRes.split(/\s+/);
if (words.includes('YES')) yes++;
else if (words.includes('NO')) no++;
else other++;
}
}
// Pass if YES > NO and YES > OTHER (plurality)
const pass = yes > no && yes > other;
return {
verdict: pass,
reasoning: rawResults,
votes: { yes, no, other },
};
}
}
+147
View File
@@ -0,0 +1,147 @@
/**
* @license
* Copyright 2026 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
import { describe, expect } from 'vitest';
import {
componentEvalTest,
type ComponentEvalCase,
} from './component-test-helper.js';
import { type EvalPolicy } from './test-helper.js';
import { SnapshotGenerator } from '@google/gemini-cli-core';
import { NodeType, type ConcreteNode } from '@google/gemini-cli-core';
import { LLMJudge } from './llm-judge.js';
function snapshotEvalTest(policy: EvalPolicy, evalCase: ComponentEvalCase) {
return componentEvalTest(policy, evalCase);
}
describe('snapshot_fidelity', () => {
snapshotEvalTest('ALWAYS_PASSES', {
suiteName: 'default',
suiteType: 'behavioral',
name: 'SnapshotGenerator strictly retains specific empirical facts',
assert: async (config) => {
// 1. Construct a highly specific mock transcript containing 3 empirical facts we can test for:
// Fact A: File path -> src/compiler/server.ts
// Fact B: Error code -> COMPILE_ERR_404
// Fact C: Active Directive -> "do not fix it just yet"
const mockNodes: ConcreteNode[] = [
{
id: '1',
turnId: '1',
type: NodeType.USER_PROMPT,
timestamp: Date.now(),
role: 'user',
payload: {
text: 'I am trying to debug a weird timeout issue when compiling the TS server.',
},
},
{
id: '2',
turnId: '2',
type: NodeType.TOOL_EXECUTION,
timestamp: Date.now() + 100,
role: 'model',
payload: {
functionCall: {
name: 'run_shell_command',
args: { cmd: 'grep -rn "timeout" src/' },
},
},
},
{
id: '3',
turnId: '2',
type: NodeType.TOOL_EXECUTION,
timestamp: Date.now() + 200,
role: 'user',
payload: {
functionResponse: {
name: 'run_shell_command',
response: {
output:
'src/compiler/server.ts:442: setTimeout(() => reject(new Error("COMPILE_ERR_404")), 5000);',
},
},
},
},
{
id: '4',
turnId: '3',
type: NodeType.AGENT_YIELD,
timestamp: Date.now() + 300,
role: 'model',
payload: {
text: 'I found the exact line. It looks like the compiler throws COMPILE_ERR_404 if it hits 5 seconds.',
},
},
{
id: '5',
turnId: '4',
type: NodeType.USER_PROMPT,
timestamp: Date.now() + 400,
role: 'user',
payload: {
text: 'Okay, do not fix it just yet. I want you to remember this error code (COMPILE_ERR_404) and file path. First, list all the files in the directory.',
},
},
];
// 2. Extract the LLM Client from the component container
const llmClient = config.getBaseLlmClient();
const generator = new SnapshotGenerator({
llmClient,
promptId: 'eval-snapshot-test',
tokenCalculator: {
estimateTokensForString(str: string): number {
return str.length * 4;
},
},
} as any);
// 3. Generate the snapshot using the CURRENT system prompt
const snapshotText = await generator.synthesizeSnapshot(mockNodes);
// 4. Use LLM-as-a-Judge with Self-Consistency to evaluate factual fidelity
const judge = new LLMJudge(llmClient);
const judgePrompt = `
EVIDENCE (CONTEXT SNAPSHOT):
"""
${snapshotText}
"""
QUESTION:
Does the EVIDENCE explicitly contain all three of the following facts:
1. The specific file path "src/compiler/server.ts"
2. The specific error code "COMPILE_ERR_404"
3. The user's active constraint/directive to "do not fix it just yet" (or equivalent warning that implementation is paused)
Answer ONLY with "YES" if all three are unambiguously present.
Answer "NO" if any of the three are missing, abstracted away, or generalized (e.g., if it says "found an error" instead of "COMPILE_ERR_404").`;
// Use a self-consistency of 3 runs to get a robust majority vote
const result = await judge.judgeYesNo(judgePrompt, {
selfConsistencyRuns: 3,
});
// 5. Assert the verdict
const formattedVotes = JSON.stringify(result.votes);
const formattedReasoning = JSON.stringify(result.reasoning);
expect(
result.verdict,
`Snapshot failed to retain empirical facts.
Votes: ${formattedVotes}
Reasoning: ${formattedReasoning}
Generated Snapshot:
${snapshotText}`,
).toBe(true);
},
});
});
+1 -3
View File
@@ -16,7 +16,6 @@ import {
Storage,
getProjectHash,
SESSION_FILE_PREFIX,
PREVIEW_GEMINI_FLASH_MODEL,
getErrorMessage,
} from '@google/gemini-cli-core';
@@ -26,8 +25,7 @@ export * from '@google/gemini-cli-test-utils';
* The default model used for all evaluations.
* Can be overridden by setting the GEMINI_MODEL environment variable.
*/
export const EVAL_MODEL =
process.env['GEMINI_MODEL'] || PREVIEW_GEMINI_FLASH_MODEL;
export const EVAL_MODEL = process.env['GEMINI_MODEL'] || 'gemini-3.5-flash';
// Indicates the consistency expectation for this test.
// - ALWAYS_PASSES - Means that the test is expected to pass 100% of the time. These
+41 -12
View File
@@ -1,12 +1,12 @@
{
"name": "@google/gemini-cli",
"version": "0.42.0-nightly.20260428.g59b2dea0e",
"version": "0.42.0-nightly.20260512.gc987b9939",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@google/gemini-cli",
"version": "0.42.0-nightly.20260428.g59b2dea0e",
"version": "0.42.0-nightly.20260512.gc987b9939",
"workspaces": [
"packages/*"
],
@@ -449,7 +449,8 @@
"version": "2.11.0",
"resolved": "https://registry.npmjs.org/@bufbuild/protobuf/-/protobuf-2.11.0.tgz",
"integrity": "sha512-sBXGT13cpmPR5BMgHE6UEEfEaShh5Ror6rfN3yEK5si7QVrtZg8LEPQb0VVhiLRUslD2yLnXtnRzG035J/mZXQ==",
"license": "(Apache-2.0 AND BSD-3-Clause)"
"license": "(Apache-2.0 AND BSD-3-Clause)",
"peer": true
},
"node_modules/@bundled-es-modules/cookie": {
"version": "2.0.1",
@@ -1535,6 +1536,7 @@
"resolved": "https://registry.npmjs.org/@grpc/grpc-js/-/grpc-js-1.13.4.tgz",
"integrity": "sha512-GsFaMXCkMqkKIvwCQjCrwH+GHbPKBjhwo/8ZuUkWHqbI73Kky9I+pQltrlT0+MWpedCoosda53lgjYfyEPgxBg==",
"license": "Apache-2.0",
"peer": true,
"dependencies": {
"@grpc/proto-loader": "^0.7.13",
"@js-sdsl/ordered-map": "^4.4.2"
@@ -2212,6 +2214,7 @@
"integrity": "sha512-t54CUOsFMappY1Jbzb7fetWeO0n6K0k/4+/ZpkS+3Joz8I4VcvY9OiEBFRYISqaI2fq5sCiPtAjRDOzVYG8m+Q==",
"dev": true,
"license": "MIT",
"peer": true,
"dependencies": {
"@octokit/auth-token": "^6.0.0",
"@octokit/graphql": "^9.0.2",
@@ -2392,6 +2395,7 @@
"resolved": "https://registry.npmjs.org/@opentelemetry/api/-/api-1.9.0.tgz",
"integrity": "sha512-3giAOQvZiH5F9bMlMiv8+GSPMeqg0dbaeo58/0SlA9sxSqZhnUtxzX9/2FzyhS9sWQf5S0GJE0AKBrFqjpeYcg==",
"license": "Apache-2.0",
"peer": true,
"engines": {
"node": ">=8.0.0"
}
@@ -2441,6 +2445,7 @@
"resolved": "https://registry.npmjs.org/@opentelemetry/core/-/core-2.5.0.tgz",
"integrity": "sha512-ka4H8OM6+DlUhSAZpONu0cPBtPPTQKxbxVzC4CzVx5+K4JnroJVBtDzLAMx4/3CDTJXRvVFhpFjtl4SaiTNoyQ==",
"license": "Apache-2.0",
"peer": true,
"dependencies": {
"@opentelemetry/semantic-conventions": "^1.29.0"
},
@@ -2815,6 +2820,7 @@
"resolved": "https://registry.npmjs.org/@opentelemetry/resources/-/resources-2.5.0.tgz",
"integrity": "sha512-F8W52ApePshpoSrfsSk1H2yJn9aKjCrbpQF1M9Qii0GHzbfVeFUB+rc3X4aggyZD8x9Gu3Slua+s6krmq6Dt8g==",
"license": "Apache-2.0",
"peer": true,
"dependencies": {
"@opentelemetry/core": "2.5.0",
"@opentelemetry/semantic-conventions": "^1.29.0"
@@ -2848,6 +2854,7 @@
"resolved": "https://registry.npmjs.org/@opentelemetry/sdk-metrics/-/sdk-metrics-2.5.0.tgz",
"integrity": "sha512-BeJLtU+f5Gf905cJX9vXFQorAr6TAfK3SPvTFqP+scfIpDQEJfRaGJWta7sJgP+m4dNtBf9y3yvBKVAZZtJQVA==",
"license": "Apache-2.0",
"peer": true,
"dependencies": {
"@opentelemetry/core": "2.5.0",
"@opentelemetry/resources": "2.5.0"
@@ -2902,6 +2909,7 @@
"resolved": "https://registry.npmjs.org/@opentelemetry/sdk-trace-base/-/sdk-trace-base-2.5.0.tgz",
"integrity": "sha512-VzRf8LzotASEyNDUxTdaJ9IRJ1/h692WyArDBInf5puLCjxbICD6XkHgpuudis56EndyS7LYFmtTMny6UABNdQ==",
"license": "Apache-2.0",
"peer": true,
"dependencies": {
"@opentelemetry/core": "2.5.0",
"@opentelemetry/resources": "2.5.0",
@@ -4139,6 +4147,7 @@
"integrity": "sha512-6mDvHUFSjyT2B2yeNx2nUgMxh9LtOWvkhIU3uePn2I2oyNymUAX1NIsdgviM4CH+JSrp2D2hsMvJOkxY+0wNRA==",
"devOptional": true,
"license": "MIT",
"peer": true,
"dependencies": {
"csstype": "^3.0.2"
}
@@ -4412,6 +4421,7 @@
"integrity": "sha512-/Zb/xaIDfxeJnvishjGdcR4jmr7S+bda8PKNhRGdljDM+elXhlvN0FyPSsMnLmJUrVG9aPO6dof80wjMawsASg==",
"dev": true,
"license": "MIT",
"peer": true,
"dependencies": {
"@typescript-eslint/scope-manager": "8.58.2",
"@typescript-eslint/types": "8.58.2",
@@ -5187,6 +5197,7 @@
"resolved": "https://registry.npmjs.org/acorn/-/acorn-8.15.0.tgz",
"integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==",
"license": "MIT",
"peer": true,
"bin": {
"acorn": "bin/acorn"
},
@@ -7304,7 +7315,8 @@
"version": "0.0.1581282",
"resolved": "https://registry.npmjs.org/devtools-protocol/-/devtools-protocol-0.0.1581282.tgz",
"integrity": "sha512-nv7iKtNZQshSW2hKzYNr46nM/Cfh5SEvE2oV0/SEGgc9XupIY5ggf84Cz8eJIkBce7S3bmTAauFD6aysMpnqsQ==",
"license": "BSD-3-Clause"
"license": "BSD-3-Clause",
"peer": true
},
"node_modules/dezalgo": {
"version": "1.0.4",
@@ -7889,6 +7901,7 @@
"integrity": "sha512-GsGizj2Y1rCWDu6XoEekL3RLilp0voSePurjZIkxL3wlm5o5EC9VpgaP7lrCvjnkuLvzFBQWB3vWB3K5KQTveQ==",
"dev": true,
"license": "MIT",
"peer": true,
"dependencies": {
"@eslint-community/eslint-utils": "^4.2.0",
"@eslint-community/regexpp": "^4.12.1",
@@ -8499,6 +8512,7 @@
"resolved": "https://registry.npmjs.org/express/-/express-5.2.1.tgz",
"integrity": "sha512-hIS4idWWai69NezIdRt2xFVofaF4j+6INOpJlVOLDO8zXGpUVEVzIYk12UUi2JzjEzWL3IOAxcTubgz9Po0yXw==",
"license": "MIT",
"peer": true,
"dependencies": {
"accepts": "^2.0.0",
"body-parser": "^2.2.1",
@@ -9765,6 +9779,7 @@
"resolved": "https://registry.npmjs.org/hono/-/hono-4.12.12.tgz",
"integrity": "sha512-p1JfQMKaceuCbpJKAPKVqyqviZdS0eUxH9v82oWo1kb9xjQ5wA6iP3FNVAPDFlz5/p7d45lO+BpSk1tuSZMF4Q==",
"license": "MIT",
"peer": true,
"engines": {
"node": ">=16.9.0"
}
@@ -10024,6 +10039,7 @@
"resolved": "https://registry.npmjs.org/@jrichman/ink/-/ink-6.6.9.tgz",
"integrity": "sha512-RL9sSiLQZECnjbmBwjIHOp8yVGdWF7C/uifg7ISv/e+F3nLNsfl7FdUFQs8iZARFMJAYxMFpxW6OW+HSt9drwQ==",
"license": "MIT",
"peer": true,
"dependencies": {
"ansi-escapes": "^7.0.0",
"ansi-styles": "^6.2.3",
@@ -13799,6 +13815,7 @@
"resolved": "https://registry.npmjs.org/react/-/react-19.2.4.tgz",
"integrity": "sha512-9nfp2hYpCwOjAN+8TZFGhtWEwgvWHXqESH8qT89AT/lWklpLON22Lc8pEtnpsZz7VmawabSU0gCjnj8aC0euHQ==",
"license": "MIT",
"peer": true,
"engines": {
"node": ">=0.10.0"
}
@@ -13809,6 +13826,7 @@
"integrity": "sha512-ePrwPfxAnB+7hgnEr8vpKxL9cmnp7F322t8oqcPshbIQQhDKgFDW4tjhF2wjVbdXF9O/nyuy3sQWd9JGpiLPvA==",
"devOptional": true,
"license": "MIT",
"peer": true,
"dependencies": {
"shell-quote": "^1.6.1",
"ws": "^7"
@@ -15961,6 +15979,7 @@
"resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.4.tgz",
"integrity": "sha512-QP88BAKvMam/3NxH6vj2o21R6MjxZUAd6nlwAS/pnGvN9IVLocLHxGYIzFhg6fUQ+5th6P4dv4eW9jX3DSIj7A==",
"license": "MIT",
"peer": true,
"engines": {
"node": ">=12"
},
@@ -16183,7 +16202,8 @@
"version": "2.8.1",
"resolved": "https://registry.npmjs.org/tslib/-/tslib-2.8.1.tgz",
"integrity": "sha512-oJFu94HQb+KVduSUQL7wnpmqnfmLsOA/nAh6b6EH0wCEoK0/mPeXU6c3wKDV83MkOuHPRHtSXKKU99IBazS/2w==",
"license": "0BSD"
"license": "0BSD",
"peer": true
},
"node_modules/tsx": {
"version": "4.20.3",
@@ -16191,6 +16211,7 @@
"integrity": "sha512-qjbnuR9Tr+FJOMBqJCW5ehvIo/buZq7vH7qD7JziU98h6l3qGy0a/yPFjwO+y0/T7GFpNgNAvEcPPVfyT8rrPQ==",
"devOptional": true,
"license": "MIT",
"peer": true,
"dependencies": {
"esbuild": "~0.25.0",
"get-tsconfig": "^4.7.5"
@@ -16356,6 +16377,7 @@
"integrity": "sha512-p1diW6TqL9L07nNxvRMM7hMMw4c5XOo/1ibL4aAIGmSAt9slTE1Xgw5KWuof2uTOvCg9BY7ZRi+GaF+7sfgPeQ==",
"devOptional": true,
"license": "Apache-2.0",
"peer": true,
"bin": {
"tsc": "bin/tsc",
"tsserver": "bin/tsserver"
@@ -16423,6 +16445,7 @@
"integrity": "sha512-6sMvZePQrnZH2/cJkwRpkT7DxoAWh+g6+GFRK6bV3YQo7ogi3SX5rgF6099r5Q53Ma5qeT7LGmOmuIutF4t3lA==",
"dev": true,
"license": "MIT",
"peer": true,
"dependencies": {
"@typescript-eslint/scope-manager": "8.35.0",
"@typescript-eslint/types": "8.35.0",
@@ -16842,6 +16865,7 @@
"resolved": "https://registry.npmjs.org/vite/-/vite-7.3.2.tgz",
"integrity": "sha512-Bby3NOsna2jsjfLVOHKes8sGwgl4TT0E6vvpYgnAYDIF/tie7MRaFthmKuHx1NSXjiTueXH3do80FMQgvEktRg==",
"license": "MIT",
"peer": true,
"dependencies": {
"esbuild": "^0.27.0",
"fdir": "^6.5.0",
@@ -17412,6 +17436,7 @@
"resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.4.tgz",
"integrity": "sha512-QP88BAKvMam/3NxH6vj2o21R6MjxZUAd6nlwAS/pnGvN9IVLocLHxGYIzFhg6fUQ+5th6P4dv4eW9jX3DSIj7A==",
"license": "MIT",
"peer": true,
"engines": {
"node": ">=12"
},
@@ -17424,6 +17449,7 @@
"resolved": "https://registry.npmjs.org/vitest/-/vitest-3.2.4.tgz",
"integrity": "sha512-LUCP5ev3GURDysTWiP47wRRUpLKMOfPh+yKTx3kVIEiu5KOMeqzpnYNsKyOoVrULivR8tLcks4+lga33Whn90A==",
"license": "MIT",
"peer": true,
"dependencies": {
"@types/chai": "^5.2.2",
"@vitest/expect": "3.2.4",
@@ -18062,6 +18088,7 @@
"resolved": "https://registry.npmjs.org/zod/-/zod-3.25.76.tgz",
"integrity": "sha512-gzUt/qt81nXsFGKIFcC3YnfEAx5NkunCfnDlvuBSSFS02bcXu4Lmea0AFIUwbLWxWPx3d9p8S5QoaujKcNQxcQ==",
"license": "MIT",
"peer": true,
"funding": {
"url": "https://github.com/sponsors/colinhacks"
}
@@ -18077,7 +18104,7 @@
},
"packages/a2a-server": {
"name": "@google/gemini-cli-a2a-server",
"version": "0.42.0-nightly.20260428.g59b2dea0e",
"version": "0.42.0-nightly.20260512.gc987b9939",
"dependencies": {
"@a2a-js/sdk": "0.3.11",
"@google-cloud/storage": "^7.16.0",
@@ -18206,7 +18233,7 @@
},
"packages/cli": {
"name": "@google/gemini-cli",
"version": "0.42.0-nightly.20260428.g59b2dea0e",
"version": "0.42.0-nightly.20260512.gc987b9939",
"license": "Apache-2.0",
"dependencies": {
"@agentclientprotocol/sdk": "^0.16.1",
@@ -18354,7 +18381,7 @@
},
"packages/core": {
"name": "@google/gemini-cli-core",
"version": "0.42.0-nightly.20260428.g59b2dea0e",
"version": "0.42.0-nightly.20260512.gc987b9939",
"license": "Apache-2.0",
"dependencies": {
"@a2a-js/sdk": "0.3.11",
@@ -18498,6 +18525,7 @@
"resolved": "https://registry.npmjs.org/@grpc/grpc-js/-/grpc-js-1.14.3.tgz",
"integrity": "sha512-Iq8QQQ/7X3Sac15oB6p0FmUg/klxQvXLeileoqrTRGJYLV+/9tubbr9ipz0GKHjmXVsgFPo/+W+2cA8eNcR+XA==",
"license": "Apache-2.0",
"peer": true,
"dependencies": {
"@grpc/proto-loader": "^0.8.0",
"@js-sdsl/ordered-map": "^4.4.2"
@@ -18616,6 +18644,7 @@
"resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.4.tgz",
"integrity": "sha512-QP88BAKvMam/3NxH6vj2o21R6MjxZUAd6nlwAS/pnGvN9IVLocLHxGYIzFhg6fUQ+5th6P4dv4eW9jX3DSIj7A==",
"license": "MIT",
"peer": true,
"engines": {
"node": ">=12"
},
@@ -18665,7 +18694,7 @@
},
"packages/devtools": {
"name": "@google/gemini-cli-devtools",
"version": "0.42.0-nightly.20260428.g59b2dea0e",
"version": "0.42.0-nightly.20260512.gc987b9939",
"license": "Apache-2.0",
"dependencies": {
"ws": "^8.16.0"
@@ -18680,7 +18709,7 @@
},
"packages/sdk": {
"name": "@google/gemini-cli-sdk",
"version": "0.42.0-nightly.20260428.g59b2dea0e",
"version": "0.42.0-nightly.20260512.gc987b9939",
"license": "Apache-2.0",
"dependencies": {
"@google/gemini-cli-core": "file:../core",
@@ -18711,7 +18740,7 @@
},
"packages/test-utils": {
"name": "@google/gemini-cli-test-utils",
"version": "0.42.0-nightly.20260428.g59b2dea0e",
"version": "0.42.0-nightly.20260512.gc987b9939",
"license": "Apache-2.0",
"dependencies": {
"@google/gemini-cli-core": "file:../core",
@@ -18743,7 +18772,7 @@
},
"packages/vscode-ide-companion": {
"name": "gemini-cli-vscode-ide-companion",
"version": "0.42.0-nightly.20260428.g59b2dea0e",
"version": "0.42.0-nightly.20260512.gc987b9939",
"license": "LICENSE",
"dependencies": {
"@modelcontextprotocol/sdk": "^1.23.0",
+2 -2
View File
@@ -1,6 +1,6 @@
{
"name": "@google/gemini-cli",
"version": "0.42.0-nightly.20260428.g59b2dea0e",
"version": "0.42.0-nightly.20260512.gc987b9939",
"engines": {
"node": ">=20.0.0"
},
@@ -14,7 +14,7 @@
"url": "git+https://github.com/google-gemini/gemini-cli.git"
},
"config": {
"sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.42.0-nightly.20260428.g59b2dea0e"
"sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.42.0-nightly.20260512.gc987b9939"
},
"scripts": {
"start": "cross-env NODE_ENV=development node scripts/start.js",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@google/gemini-cli-a2a-server",
"version": "0.42.0-nightly.20260428.g59b2dea0e",
"version": "0.42.0-nightly.20260512.gc987b9939",
"description": "Gemini CLI A2A Server",
"repository": {
"type": "git",
+2 -2
View File
@@ -1,6 +1,6 @@
{
"name": "@google/gemini-cli",
"version": "0.42.0-nightly.20260428.g59b2dea0e",
"version": "0.42.0-nightly.20260512.gc987b9939",
"description": "Gemini CLI",
"license": "Apache-2.0",
"repository": {
@@ -27,7 +27,7 @@
"dist"
],
"config": {
"sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.42.0-nightly.20260428.g59b2dea0e"
"sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.42.0-nightly.20260512.gc987b9939"
},
"dependencies": {
"@agentclientprotocol/sdk": "^0.16.1",
+6 -11
View File
@@ -19,6 +19,7 @@ import type * as acp from '@agentclientprotocol/sdk';
import {
AuthType,
type Config,
GEMINI_MODEL_ALIAS_AUTO,
type MessageBus,
type Storage,
} from '@google/gemini-cli-core';
@@ -208,20 +209,19 @@ describe('AcpSessionManager', () => {
expect(response.models?.availableModels).toEqual(
expect.arrayContaining([
expect.objectContaining({
modelId: 'auto-gemini-3',
modelId: GEMINI_MODEL_ALIAS_AUTO,
name: expect.stringContaining('Auto'),
}),
]),
);
});
it('should include gemini-3.1-flash-lite when useGemini31FlashLite is true', async () => {
it('should NOT include retired preview models (none) in available models', async () => {
mockConfig.getContentGeneratorConfig = vi.fn().mockReturnValue({
apiKey: 'test-key',
});
mockConfig.getHasAccessToPreviewModel = vi.fn().mockReturnValue(true);
mockConfig.getGemini31LaunchedSync = vi.fn().mockReturnValue(true);
mockConfig.getGemini31FlashLiteLaunchedSync = vi.fn().mockReturnValue(true);
const response = await manager.newSession(
{
@@ -231,14 +231,9 @@ describe('AcpSessionManager', () => {
{},
);
expect(response.models?.availableModels).toEqual(
expect.arrayContaining([
expect.objectContaining({
modelId: 'gemini-3.1-flash-lite-preview',
name: 'gemini-3.1-flash-lite-preview',
}),
]),
);
const modelIds =
response.models?.availableModels?.map((m) => m.modelId) ?? [];
expect(modelIds).not.toContain('none');
});
it('should return modes with plan mode when plan is enabled', async () => {
+28 -31
View File
@@ -10,8 +10,7 @@ import {
type ToolCallConfirmationDetails,
Kind,
ApprovalMode,
DEFAULT_GEMINI_MODEL_AUTO,
PREVIEW_GEMINI_MODEL_AUTO,
GEMINI_MODEL_ALIAS_AUTO,
DEFAULT_GEMINI_MODEL,
DEFAULT_GEMINI_FLASH_MODEL,
DEFAULT_GEMINI_FLASH_LITE_MODEL,
@@ -19,10 +18,11 @@ import {
PREVIEW_GEMINI_MODEL,
PREVIEW_GEMINI_3_1_CUSTOM_TOOLS_MODEL,
PREVIEW_GEMINI_FLASH_MODEL,
PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL,
PREVIEW_GEMINI_FLASH_LITE_MODEL,
getDisplayString,
AuthType,
ToolConfirmationOutcome,
getAutoModelDescription,
} from '@google/gemini-cli-core';
import type * as acp from '@agentclientprotocol/sdk';
import { z } from 'zod';
@@ -262,11 +262,10 @@ export function buildAvailableModels(
}>;
currentModelId: string;
} {
const preferredModel = config.getModel() || DEFAULT_GEMINI_MODEL_AUTO;
const preferredModel = config.getModel() || GEMINI_MODEL_ALIAS_AUTO;
const shouldShowPreviewModels = config.getHasAccessToPreviewModel();
const useGemini31 = config.getGemini31LaunchedSync?.() ?? false;
const useGemini31FlashLite =
config.getGemini31FlashLiteLaunchedSync?.() ?? false;
const useGemini3_5Flash = config.hasGemini35FlashGAAccess?.() ?? false;
const selectedAuthType = settings.merged.security.auth.selectedType;
const useCustomToolModel =
useGemini31 && selectedAuthType === AuthType.USE_GEMINI;
@@ -278,7 +277,7 @@ export function buildAvailableModels(
) {
const options = config.getModelConfigService().getAvailableModelOptions({
useGemini3_1: useGemini31,
useGemini3_1FlashLite: useGemini31FlashLite,
useGemini3_5Flash,
useCustomTools: useCustomToolModel,
hasAccessToPreview: shouldShowPreviewModels,
});
@@ -290,37 +289,35 @@ export function buildAvailableModels(
}
// --- LEGACY PATH ---
const defaultFlashModel =
config.getDefaultGeminiFlashModel?.() ?? DEFAULT_GEMINI_FLASH_MODEL;
const previewFlashModel =
config.getPreviewGeminiFlashModel?.() ?? PREVIEW_GEMINI_FLASH_MODEL;
const mainOptions = [
{
value: DEFAULT_GEMINI_MODEL_AUTO,
title: getDisplayString(DEFAULT_GEMINI_MODEL_AUTO),
description:
'Let Gemini CLI decide the best model for the task: gemini-2.5-pro, gemini-2.5-flash',
value: GEMINI_MODEL_ALIAS_AUTO,
title: getDisplayString(GEMINI_MODEL_ALIAS_AUTO, config),
description: getAutoModelDescription(
shouldShowPreviewModels,
useGemini31,
useGemini3_5Flash,
),
},
];
if (shouldShowPreviewModels) {
mainOptions.unshift({
value: PREVIEW_GEMINI_MODEL_AUTO,
title: getDisplayString(PREVIEW_GEMINI_MODEL_AUTO),
description: useGemini31
? 'Let Gemini CLI decide the best model for the task: gemini-3.1-pro, gemini-3-flash'
: 'Let Gemini CLI decide the best model for the task: gemini-3-pro, gemini-3-flash',
});
}
const manualOptions = [
{
value: DEFAULT_GEMINI_MODEL,
title: getDisplayString(DEFAULT_GEMINI_MODEL),
title: getDisplayString(DEFAULT_GEMINI_MODEL, config),
},
{
value: DEFAULT_GEMINI_FLASH_MODEL,
title: getDisplayString(DEFAULT_GEMINI_FLASH_MODEL),
value: defaultFlashModel,
title: getDisplayString(defaultFlashModel, config),
},
{
value: DEFAULT_GEMINI_FLASH_LITE_MODEL,
title: getDisplayString(DEFAULT_GEMINI_FLASH_LITE_MODEL),
title: getDisplayString(DEFAULT_GEMINI_FLASH_LITE_MODEL, config),
},
];
@@ -336,18 +333,18 @@ export function buildAvailableModels(
const previewOptions = [
{
value: previewProValue,
title: getDisplayString(previewProModel),
title: getDisplayString(previewProModel, config),
},
{
value: PREVIEW_GEMINI_FLASH_MODEL,
title: getDisplayString(PREVIEW_GEMINI_FLASH_MODEL),
value: previewFlashModel,
title: getDisplayString(previewFlashModel, config),
},
];
if (useGemini31FlashLite) {
if (PREVIEW_GEMINI_FLASH_LITE_MODEL !== 'none') {
previewOptions.push({
value: PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL,
title: getDisplayString(PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL),
value: PREVIEW_GEMINI_FLASH_LITE_MODEL,
title: getDisplayString(PREVIEW_GEMINI_FLASH_LITE_MODEL, config),
});
}
+22
View File
@@ -1043,6 +1043,28 @@ describe('loadCliConfig', () => {
expect(config.isInteractive()).toBe(false);
});
describe('isAcpMode', () => {
it('should force skipNextSpeakerCheck to true when in ACP mode', async () => {
process.argv = ['node', 'script.js', '--acp'];
const argv = await parseArguments(createTestMergedSettings());
const settings = createTestMergedSettings({
model: { skipNextSpeakerCheck: false },
});
const config = await loadCliConfig(settings, 'test-session', argv);
expect(config.getSkipNextSpeakerCheck()).toBe(true);
});
it('should respect settings.model.skipNextSpeakerCheck when not in ACP mode', async () => {
process.argv = ['node', 'script.js'];
const argv = await parseArguments(createTestMergedSettings());
const settings = createTestMergedSettings({
model: { skipNextSpeakerCheck: false },
});
const config = await loadCliConfig(settings, 'test-session', argv);
expect(config.getSkipNextSpeakerCheck()).toBe(false);
});
});
});
describe('Hierarchical Memory Loading (config.ts) - Placeholder Suite', () => {
+5 -1
View File
@@ -1105,7 +1105,11 @@ export async function loadCliConfig(
shellToolInactivityTimeout: settings.tools?.shell?.inactivityTimeout,
enableShellOutputEfficiency:
settings.tools?.shell?.enableShellOutputEfficiency ?? true,
skipNextSpeakerCheck: settings.model?.skipNextSpeakerCheck,
// In ACP mode, always skip the next-speaker check. This check triggers
// recursive continuation turns inside GeminiClient.processTurn() that
// conflict with ACP's explicit turn management via session/prompt,
// causing infinite agent_thought_chunk loops.
skipNextSpeakerCheck: isAcpMode || settings.model?.skipNextSpeakerCheck,
truncateToolOutputThreshold: settings.tools?.truncateToolOutputThreshold,
eventEmitter: coreEvents,
useWriteTodos: argv.useWriteTodos ?? settings.useWriteTodos,
+2 -1
View File
@@ -1300,7 +1300,8 @@ export async function inferInstallMetadata(
source.startsWith('git@') ||
source.startsWith('sso://') ||
source.startsWith('github:') ||
source.startsWith('gitlab:')
source.startsWith('gitlab:') ||
source.startsWith('ssh://')
) {
return {
source,
+33
View File
@@ -1189,6 +1189,39 @@ describe('resolveSessionId', () => {
expect(sessionId).toBe('new-id');
expect(resumedSessionData).toBeUndefined();
});
it('should exit with FATAL_INPUT_ERROR when explicit resume session is missing', async () => {
vi.mocked(SessionSelector).mockImplementation(
() =>
({
resolveSession: vi
.fn()
.mockRejectedValue(SessionError.noSessionsFound()),
}) as unknown as InstanceType<typeof SessionSelector>,
);
const emitFeedbackSpy = vi.spyOn(coreEvents, 'emitFeedback');
const processExitSpy = vi
.spyOn(process, 'exit')
.mockImplementation((code) => {
throw new MockProcessExitError(code);
});
try {
await resolveSessionId('explicit-session-id');
} catch (e) {
if (!(e instanceof MockProcessExitError)) throw e;
}
expect(emitFeedbackSpy).toHaveBeenCalledWith(
'error',
expect.stringContaining('Error resuming session:'),
);
expect(processExitSpy).toHaveBeenCalledWith(ExitCodes.FATAL_INPUT_ERROR);
emitFeedbackSpy.mockRestore();
processExitSpy.mockRestore();
});
});
describe('gemini.tsx main function exit codes', () => {
+9 -3
View File
@@ -85,7 +85,11 @@ import { validateAuthMethod } from './config/auth.js';
import { runAcpClient } from './acp/acpStdioTransport.js';
import { validateNonInteractiveAuth } from './validateNonInterActiveAuth.js';
import { appEvents, AppEvent } from './utils/events.js';
import { SessionError, SessionSelector } from './utils/sessionUtils.js';
import {
RESUME_LATEST,
SessionError,
SessionSelector,
} from './utils/sessionUtils.js';
import { relaunchOnExitCode } from './utils/relaunch.js';
import { loadSandboxConfig } from './config/sandboxConfig.js';
@@ -309,8 +313,10 @@ export async function resolveSessionId(
};
} catch (error) {
if (error instanceof SessionError && error.code === 'NO_SESSIONS_FOUND') {
coreEvents.emitFeedback('warning', error.message);
return { sessionId: createSessionId() };
if (resumeArg === RESUME_LATEST) {
coreEvents.emitFeedback('warning', error.message);
return { sessionId: createSessionId() };
}
}
coreEvents.emitFeedback(
'error',
+3
View File
@@ -68,6 +68,9 @@ export async function runNonInteractive(
): Promise<void> {
const useAgentSession = params.config.getAgentSessionNoninteractiveEnabled();
if (useAgentSession) {
debugLogger.debug(
'[ADK] Running non-interactive mode with ADK agent session',
);
return runNonInteractiveAgentSession(params);
}
+36
View File
@@ -1267,6 +1267,42 @@ describe('AppContainer State Management', () => {
});
});
describe('SessionStart Hook Rendering', () => {
it('does not render systemMessage directly (avoids duplicate with HookSystemMessage event)', async () => {
const mockAddItem = vi.fn();
mockedUseHistory.mockReturnValue({
history: [],
addItem: mockAddItem,
updateItem: vi.fn(),
clearItems: vi.fn(),
loadHistory: vi.fn(),
});
const fireSessionStartEvent = vi.fn().mockResolvedValue({
systemMessage: 'Hello from SessionStart hook',
getAdditionalContext: vi.fn(() => undefined),
});
vi.spyOn(mockConfig, 'getHookSystem').mockReturnValue({
fireSessionEndEvent: vi.fn().mockResolvedValue(undefined),
fireSessionStartEvent,
} as unknown as ReturnType<Config['getHookSystem']>);
const { unmount } = await act(async () => renderAppContainer());
await waitFor(() => expect(fireSessionStartEvent).toHaveBeenCalled());
// The direct-render path (the bug) would call addItem with the
// systemMessage text and no `source` field. The HookSystemMessage
// event-listener path (the correct one) always sets `source`.
const directRenderCall = mockAddItem.mock.calls.find(
([item]) =>
item?.text === 'Hello from SessionStart hook' && !item?.source,
);
expect(directRenderCall).toBeUndefined();
unmount();
});
});
describe('Token Counting from Session Stats', () => {
it('tracks token counts from session messages', async () => {
// Session stats are provided through the SessionStatsProvider context
-16
View File
@@ -497,16 +497,6 @@ export const AppContainer = (props: AppContainerProps) => {
?.fireSessionStartEvent(sessionStartSource);
if (result) {
if (result.systemMessage) {
historyManager.addItem(
{
type: MessageType.INFO,
text: result.systemMessage,
},
Date.now(),
);
}
const additionalContext = result.getAdditionalContext();
const geminiClient = config.getGeminiClient();
if (additionalContext && geminiClient) {
@@ -549,12 +539,6 @@ export const AppContainer = (props: AppContainerProps) => {
debugLogger.error('Error during cleanup:', e),
);
};
// Disable the dependencies check here. historyManager gets flagged
// but we don't want to react to changes to it because each new history
// item, including the ones from the start session hook will cause a
// re-render and an error when we try to reload config.
//
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [config, resumedSessionData]);
useEffect(
@@ -5332,6 +5332,34 @@ describe('InputPrompt', () => {
});
});
});
describe('terminal buffer rendering', () => {
it('does not clip the last char of a visual line whose width equals inputWidth', async () => {
const fullLine = '1234567890'; // 10 chars, exactly props.inputWidth
props.inputWidth = 10;
props.suggestionsWidth = 10;
vi.spyOn(props.config, 'getUseTerminalBuffer').mockReturnValue(true);
mockBuffer.text = fullLine;
mockBuffer.lines = [fullLine];
mockBuffer.allVisualLines = [fullLine];
mockBuffer.viewportVisualLines = [fullLine];
mockBuffer.visualToLogicalMap = [[0, 0]];
mockBuffer.visualToTransformedMap = [0];
mockBuffer.transformationsByLine = [[]];
mockBuffer.cursor = [0, fullLine.length];
mockBuffer.visualCursor = [0, fullLine.length];
const { lastFrame, unmount } = await renderWithProviders(
<TestInputPrompt {...props} />,
{ uiActions },
);
await waitFor(() => {
expect(clean(lastFrame())).toContain(fullLine);
});
unmount();
});
});
});
function clean(str: string | undefined): string {
@@ -93,6 +93,8 @@ import { useIsHelpDismissKey } from '../utils/shortcutsHelp.js';
import { useRepeatedKeyPress } from '../hooks/useRepeatedKeyPress.js';
import { useKeyMatchers } from '../hooks/useKeyMatchers.js';
const SCROLLBAR_GUTTER_WIDTH = 1;
/**
* Returns if the terminal can be trusted to handle paste events atomically
* rather than potentially sending multiple paste events separated by line
@@ -1868,7 +1870,7 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
? `line-${item.absoluteVisualIdx}`
: `ghost-${item.index}`
}
width={inputWidth}
width={inputWidth + SCROLLBAR_GUTTER_WIDTH}
backgroundColor={listBackgroundColor}
containerHeight={Math.min(
buffer.viewportHeight,
@@ -12,14 +12,14 @@ import { waitFor } from '../../test-utils/async.js';
import { createMockSettings } from '../../test-utils/settings.js';
import {
DEFAULT_GEMINI_MODEL,
DEFAULT_GEMINI_MODEL_AUTO,
GEMINI_MODEL_ALIAS_AUTO,
DEFAULT_GEMINI_FLASH_MODEL,
DEFAULT_GEMINI_FLASH_LITE_MODEL,
PREVIEW_GEMINI_MODEL,
PREVIEW_GEMINI_3_1_MODEL,
PREVIEW_GEMINI_3_1_CUSTOM_TOOLS_MODEL,
PREVIEW_GEMINI_FLASH_MODEL,
PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL,
PREVIEW_GEMINI_FLASH_LITE_MODEL,
AuthType,
} from '@google/gemini-cli-core';
import type { Config, ModelSlashCommandEvent } from '@google/gemini-cli-core';
@@ -34,6 +34,11 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
await importOriginal<typeof import('@google/gemini-cli-core')>();
return {
...actual,
getAutoModelDescription: (
hasAccessToPreview: boolean,
useGemini3_1?: boolean,
) =>
`Auto Model Description (preview: ${hasAccessToPreview}, 3.1: ${useGemini3_1})`,
getDisplayString: (val: string) => mockGetDisplayString(val),
logModelSlashCommand: (config: Config, event: ModelSlashCommandEvent) =>
mockLogModelSlashCommand(config, event),
@@ -42,7 +47,7 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
mockModelSlashCommandEvent(model);
}
},
PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL: 'gemini-3.1-flash-lite-preview',
PREVIEW_GEMINI_FLASH_LITE_MODEL: 'none',
};
});
@@ -62,7 +67,6 @@ describe('<ModelDialog />', () => {
getHasAccessToPreviewModel: () => boolean;
getIdeMode: () => boolean;
getGemini31LaunchedSync: () => boolean;
getGemini31FlashLiteLaunchedSync: () => boolean;
getProModelNoAccess: () => Promise<boolean>;
getProModelNoAccessSync: () => boolean;
getExperimentalGemma: () => boolean;
@@ -83,7 +87,6 @@ describe('<ModelDialog />', () => {
getHasAccessToPreviewModel: mockGetHasAccessToPreviewModel,
getIdeMode: () => false,
getGemini31LaunchedSync: mockGetGemini31LaunchedSync,
getGemini31FlashLiteLaunchedSync: mockGetGemini31FlashLiteLaunchedSync,
getProModelNoAccess: mockGetProModelNoAccess,
getProModelNoAccessSync: mockGetProModelNoAccessSync,
getExperimentalGemma: () => false,
@@ -93,17 +96,15 @@ describe('<ModelDialog />', () => {
beforeEach(() => {
vi.resetAllMocks();
mockGetModel.mockReturnValue(DEFAULT_GEMINI_MODEL_AUTO);
mockGetModel.mockReturnValue(GEMINI_MODEL_ALIAS_AUTO);
mockGetHasAccessToPreviewModel.mockReturnValue(false);
mockGetGemini31LaunchedSync.mockReturnValue(false);
mockGetGemini31FlashLiteLaunchedSync.mockReturnValue(false);
mockGetProModelNoAccess.mockResolvedValue(false);
mockGetProModelNoAccessSync.mockReturnValue(false);
// Default implementation for getDisplayString
mockGetDisplayString.mockImplementation((val: string) => {
if (val === 'auto-gemini-2.5') return 'Auto (Gemini 2.5)';
if (val === 'auto-gemini-3') return 'Auto (Preview)';
if (val === 'auto') return 'Auto';
return val;
});
});
@@ -153,17 +154,13 @@ describe('<ModelDialog />', () => {
expect(output).not.toContain(DEFAULT_GEMINI_MODEL);
expect(output).not.toContain(PREVIEW_GEMINI_MODEL);
// Verify order: Flash Preview -> Flash Lite Preview -> Flash -> Flash Lite
// Verify order: Flash Preview -> Flash Lite (Preview/Default) -> Flash
const flashPreviewIdx = output.indexOf(PREVIEW_GEMINI_FLASH_MODEL);
const flashLitePreviewIdx = output.indexOf(
PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL,
);
const flashIdx = output.indexOf(DEFAULT_GEMINI_FLASH_MODEL);
const flashLiteIdx = output.indexOf(DEFAULT_GEMINI_FLASH_LITE_MODEL);
const flashIdx = output.indexOf(DEFAULT_GEMINI_FLASH_MODEL);
expect(flashPreviewIdx).toBeLessThan(flashLitePreviewIdx);
expect(flashLitePreviewIdx).toBeLessThan(flashIdx);
expect(flashIdx).toBeLessThan(flashLiteIdx);
expect(flashPreviewIdx).toBeLessThan(flashLiteIdx);
expect(flashLiteIdx).toBeLessThan(flashIdx);
expect(output).not.toContain('Auto');
unmount();
@@ -234,7 +231,7 @@ describe('<ModelDialog />', () => {
await waitFor(() => {
expect(mockSetModel).toHaveBeenCalledWith(
DEFAULT_GEMINI_MODEL_AUTO,
GEMINI_MODEL_ALIAS_AUTO,
true, // Session only by default
);
expect(mockOnClose).toHaveBeenCalled();
@@ -292,7 +289,7 @@ describe('<ModelDialog />', () => {
await waitFor(() => {
expect(mockSetModel).toHaveBeenCalledWith(
DEFAULT_GEMINI_MODEL_AUTO,
GEMINI_MODEL_ALIAS_AUTO,
false, // Persist enabled
);
expect(mockOnClose).toHaveBeenCalled();
@@ -355,7 +352,7 @@ describe('<ModelDialog />', () => {
mockGetModel.mockReturnValue(DEFAULT_GEMINI_MODEL);
mockGetDisplayString.mockImplementation((val: string) => {
if (val === DEFAULT_GEMINI_MODEL) return 'My Custom Model Display';
if (val === 'auto-gemini-2.5') return 'Auto (Gemini 2.5)';
if (val === 'auto') return 'Auto';
return val;
});
const { lastFrame, unmount } = await renderComponent();
@@ -369,9 +366,9 @@ describe('<ModelDialog />', () => {
mockGetHasAccessToPreviewModel.mockReturnValue(true);
});
it('shows Auto (Preview) in main view when access is granted', async () => {
it('shows Auto in main view when access is granted', async () => {
const { lastFrame, unmount } = await renderComponent();
expect(lastFrame()).toContain('Auto (Preview)');
expect(lastFrame()).toContain('Auto');
unmount();
});
@@ -449,7 +446,7 @@ describe('<ModelDialog />', () => {
unmount();
});
it('shows Flash Lite Preview model regardless of tier when flag is enabled', async () => {
it('does not show Flash Lite Preview model when it is retired (none) even if flag is enabled', async () => {
mockGetProModelNoAccessSync.mockReturnValue(false);
mockGetProModelNoAccess.mockResolvedValue(false);
mockGetHasAccessToPreviewModel.mockReturnValue(true);
@@ -468,7 +465,8 @@ describe('<ModelDialog />', () => {
await waitUntilReady();
const output = lastFrame();
expect(output).toContain(PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL);
expect(output).not.toContain(PREVIEW_GEMINI_FLASH_LITE_MODEL);
expect(output).toContain(DEFAULT_GEMINI_FLASH_LITE_MODEL);
unmount();
});
});
+68 -49
View File
@@ -13,12 +13,11 @@ import {
PREVIEW_GEMINI_MODEL,
PREVIEW_GEMINI_3_1_MODEL,
PREVIEW_GEMINI_FLASH_MODEL,
PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL,
PREVIEW_GEMINI_MODEL_AUTO,
PREVIEW_GEMINI_FLASH_LITE_MODEL,
DEFAULT_GEMINI_MODEL,
DEFAULT_GEMINI_FLASH_MODEL,
DEFAULT_GEMINI_FLASH_LITE_MODEL,
DEFAULT_GEMINI_MODEL_AUTO,
GEMINI_MODEL_ALIAS_AUTO,
GEMMA_4_31B_IT_MODEL,
GEMMA_4_26B_A4B_IT_MODEL,
ModelSlashCommandEvent,
@@ -27,6 +26,7 @@ import {
AuthType,
PREVIEW_GEMINI_3_1_CUSTOM_TOOLS_MODEL,
isProModel,
getAutoModelDescription,
} from '@google/gemini-cli-core';
import { useKeypress } from '../hooks/useKeypress.js';
import { theme } from '../semantic-colors.js';
@@ -63,12 +63,11 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
}, [config]);
// Determine the Preferred Model (read once when the dialog opens).
const preferredModel = config?.getModel() || DEFAULT_GEMINI_MODEL_AUTO;
const preferredModel = config?.getModel() || GEMINI_MODEL_ALIAS_AUTO;
const shouldShowPreviewModels = config?.getHasAccessToPreviewModel();
const shouldShowPreviewModels = config?.getHasAccessToPreviewModel() ?? false;
const useGemini31 = config?.getGemini31LaunchedSync?.() ?? false;
const useGemini31FlashLite =
config?.getGemini31FlashLiteLaunchedSync?.() ?? false;
const useGemini3_5Flash = config?.hasGemini35FlashGAAccess?.() ?? false;
const selectedAuthType = settings.merged.security.auth.selectedType;
const useCustomToolModel =
useGemini31 && selectedAuthType === AuthType.USE_GEMINI;
@@ -87,16 +86,21 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
: '';
}
const defaultFlashModel =
config?.getDefaultGeminiFlashModel?.() ?? DEFAULT_GEMINI_FLASH_MODEL;
const previewFlashModel =
config?.getPreviewGeminiFlashModel?.() ?? PREVIEW_GEMINI_FLASH_MODEL;
const manualModels = [
DEFAULT_GEMINI_MODEL,
DEFAULT_GEMINI_FLASH_MODEL,
defaultFlashModel,
DEFAULT_GEMINI_FLASH_LITE_MODEL,
PREVIEW_GEMINI_MODEL,
PREVIEW_GEMINI_3_1_MODEL,
PREVIEW_GEMINI_3_1_CUSTOM_TOOLS_MODEL,
PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL,
PREVIEW_GEMINI_FLASH_MODEL,
];
PREVIEW_GEMINI_FLASH_LITE_MODEL,
previewFlashModel,
].filter((m) => m !== 'none');
if (manualModels.includes(preferredModel)) {
return preferredModel;
}
@@ -121,7 +125,6 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
},
{ isActive: true },
);
const mainOptions = useMemo(() => {
// --- DYNAMIC PATH ---
if (
@@ -132,7 +135,7 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
.getModelConfigService()
.getAvailableModelOptions({
useGemini3_1: useGemini31,
useGemini3_1FlashLite: useGemini31FlashLite,
useGemini3_5Flash,
useCustomTools: useCustomToolModel,
hasAccessToPreview: shouldShowPreviewModels,
hasAccessToProModel,
@@ -161,11 +164,14 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
// --- LEGACY PATH ---
const list = [
{
value: DEFAULT_GEMINI_MODEL_AUTO,
title: getDisplayString(DEFAULT_GEMINI_MODEL_AUTO),
description:
'Let Gemini CLI decide the best model for the task: gemini-2.5-pro, gemini-2.5-flash',
key: DEFAULT_GEMINI_MODEL_AUTO,
value: GEMINI_MODEL_ALIAS_AUTO,
title: getDisplayString(GEMINI_MODEL_ALIAS_AUTO),
description: getAutoModelDescription(
shouldShowPreviewModels,
useGemini31,
useGemini3_5Flash,
),
key: GEMINI_MODEL_ALIAS_AUTO,
},
{
value: 'Manual',
@@ -177,23 +183,13 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
},
];
if (shouldShowPreviewModels) {
list.unshift({
value: PREVIEW_GEMINI_MODEL_AUTO,
title: getDisplayString(PREVIEW_GEMINI_MODEL_AUTO),
description: useGemini31
? 'Let Gemini CLI decide the best model for the task: gemini-3.1-pro, gemini-3-flash'
: 'Let Gemini CLI decide the best model for the task: gemini-3-pro, gemini-3-flash',
key: PREVIEW_GEMINI_MODEL_AUTO,
});
}
return list;
}, [
config,
shouldShowPreviewModels,
manualModelSelected,
useGemini31,
useGemini31FlashLite,
useGemini3_5Flash,
useCustomToolModel,
hasAccessToProModel,
]);
@@ -208,7 +204,7 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
.getModelConfigService()
.getAvailableModelOptions({
useGemini3_1: useGemini31,
useGemini3_1FlashLite: useGemini31FlashLite,
useGemini3_5Flash,
useCustomTools: useCustomToolModel,
hasAccessToPreview: shouldShowPreviewModels,
hasAccessToProModel,
@@ -225,22 +221,29 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
// --- LEGACY PATH ---
const showGemmaModels = config?.getExperimentalGemma() ?? false;
const defaultFlashModel =
config?.getDefaultGeminiFlashModel?.() ?? DEFAULT_GEMINI_FLASH_MODEL;
const previewFlashModel =
config?.getPreviewGeminiFlashModel?.() ?? PREVIEW_GEMINI_FLASH_MODEL;
const options = [
{
value: DEFAULT_GEMINI_MODEL,
title: getDisplayString(DEFAULT_GEMINI_MODEL),
title: getDisplayString(DEFAULT_GEMINI_MODEL, config ?? undefined),
key: DEFAULT_GEMINI_MODEL,
},
{
value: DEFAULT_GEMINI_FLASH_MODEL,
title: getDisplayString(DEFAULT_GEMINI_FLASH_MODEL),
key: DEFAULT_GEMINI_FLASH_MODEL,
value: DEFAULT_GEMINI_FLASH_LITE_MODEL,
title: getDisplayString(
DEFAULT_GEMINI_FLASH_LITE_MODEL,
config ?? undefined,
),
key: DEFAULT_GEMINI_FLASH_LITE_MODEL,
},
{
value: DEFAULT_GEMINI_FLASH_LITE_MODEL,
title: getDisplayString(DEFAULT_GEMINI_FLASH_LITE_MODEL),
key: DEFAULT_GEMINI_FLASH_LITE_MODEL,
value: defaultFlashModel,
title: getDisplayString(defaultFlashModel, config ?? undefined),
key: defaultFlashModel,
},
];
@@ -248,12 +251,15 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
options.push(
{
value: GEMMA_4_31B_IT_MODEL,
title: getDisplayString(GEMMA_4_31B_IT_MODEL),
title: getDisplayString(GEMMA_4_31B_IT_MODEL, config ?? undefined),
key: GEMMA_4_31B_IT_MODEL,
},
{
value: GEMMA_4_26B_A4B_IT_MODEL,
title: getDisplayString(GEMMA_4_26B_A4B_IT_MODEL),
title: getDisplayString(
GEMMA_4_26B_A4B_IT_MODEL,
config ?? undefined,
),
key: GEMMA_4_26B_A4B_IT_MODEL,
},
);
@@ -271,21 +277,24 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
const previewOptions = [
{
value: previewProValue,
title: getDisplayString(previewProModel),
title: getDisplayString(previewProModel, config ?? undefined),
key: previewProModel,
},
{
value: PREVIEW_GEMINI_FLASH_MODEL,
title: getDisplayString(PREVIEW_GEMINI_FLASH_MODEL),
key: PREVIEW_GEMINI_FLASH_MODEL,
value: previewFlashModel,
title: getDisplayString(previewFlashModel, config ?? undefined),
key: previewFlashModel,
},
];
if (useGemini31FlashLite) {
if (PREVIEW_GEMINI_FLASH_LITE_MODEL !== 'none') {
previewOptions.push({
value: PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL,
title: getDisplayString(PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL),
key: PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL,
value: PREVIEW_GEMINI_FLASH_LITE_MODEL,
title: getDisplayString(
PREVIEW_GEMINI_FLASH_LITE_MODEL,
config ?? undefined,
),
key: PREVIEW_GEMINI_FLASH_LITE_MODEL,
});
}
@@ -301,13 +310,23 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
}, [
shouldShowPreviewModels,
useGemini31,
useGemini31FlashLite,
useGemini3_5Flash,
useCustomToolModel,
hasAccessToProModel,
config,
]);
const options = view === 'main' ? mainOptions : manualOptions;
const options = useMemo(() => {
const rawOptions = view === 'main' ? mainOptions : manualOptions;
const seen = new Set<string>();
return rawOptions.filter((option) => {
if (seen.has(option.value)) {
return false;
}
seen.add(option.value);
return true;
});
}, [view, mainOptions, manualOptions]);
// Calculate the initial index based on the preferred model.
const initialIndex = useMemo(() => {
@@ -353,6 +353,49 @@ describe('<ModelStatsDisplay />', () => {
unmount();
});
it('should resolve gemini-3-flash to gemini-3.5-flash via getDisplayString', async () => {
const { lastFrame, unmount } = await renderWithMockedStats({
models: {
'gemini-3-flash': {
api: { totalRequests: 1, totalErrors: 0, totalLatencyMs: 100 },
tokens: {
input: 5,
prompt: 10,
candidates: 20,
total: 30,
cached: 5,
thoughts: 2,
tool: 1,
},
roles: {},
},
},
tools: {
totalCalls: 0,
totalSuccess: 0,
totalFail: 0,
totalDurationMs: 0,
totalDecisions: {
accept: 0,
reject: 0,
modify: 0,
[ToolCallDecision.AUTO_ACCEPT]: 0,
},
byName: {},
},
files: {
totalLinesAdded: 0,
totalLinesRemoved: 0,
},
});
const output = lastFrame();
expect(output).toContain('gemini-3.5-flash');
expect(output).not.toContain('gemini-3-flash');
expect(output).toMatchSnapshot();
unmount();
});
it('should handle models with long names (gemini-3-*-preview) without layout breaking', async () => {
const { lastFrame, unmount } = await renderWithMockedStats(
{
@@ -299,7 +299,7 @@ export const ModelStatsDisplay: React.FC<ModelStatsDisplayProps> = ({
},
...modelNames.map((name) => ({
key: name,
header: name,
header: getDisplayString(name),
flexGrow: 1,
renderCell: (row: StatRowData) => {
// Don't render anything for section headers in model columns
@@ -562,6 +562,13 @@ export const useSessionBrowserInput = (
state.setActiveIndex(0);
state.setScrollOffset(0);
return true;
} else if (key.name === 'enter') {
const selectedSession =
state.filteredAndSortedSessions[state.activeIndex];
if (selectedSession && !selectedSession.isCurrentSession) {
onResumeSession(selectedSession);
}
return true;
} else if (
key.sequence &&
key.sequence.length === 1 &&
@@ -6,6 +6,12 @@ Sort: s Reverse: r First/Last: g/G
"
`;
exports[`SessionBrowser Search and Navigation Components > NavigationHelp renders correctly 2`] = `
"Navigate: ↑/↓ Resume: Enter Search: / Delete: x Quit: q
Sort: s Reverse: r First/Last: g/G
"
`;
exports[`SessionBrowser Search and Navigation Components > NoResultsDisplay renders correctly 1`] = `
"
No sessions found matching 'no match'.
@@ -6,6 +6,12 @@ exports[`SessionBrowser UI States > SessionBrowserEmpty renders correctly 1`] =
"
`;
exports[`SessionBrowser UI States > SessionBrowserEmpty renders correctly 2`] = `
" No auto-saved conversations found.
Press q to exit
"
`;
exports[`SessionBrowser UI States > SessionBrowserError renders correctly 1`] = `
" Error: Test error message
Press q to exit
@@ -131,6 +131,33 @@ describe('<StatsDisplay />', () => {
expect(output).toMatchSnapshot();
});
it('resolves gemini-3-flash to gemini-3.5-flash in the model usage table', async () => {
const metrics = createTestMetrics({
models: {
'gemini-3-flash': {
api: { totalRequests: 5, totalErrors: 0, totalLatencyMs: 3000 },
tokens: {
input: 1000,
prompt: 2000,
candidates: 3000,
total: 5000,
cached: 500,
thoughts: 100,
tool: 50,
},
roles: {},
},
},
});
const { lastFrame } = await renderWithMockedStats(metrics);
const output = lastFrame();
expect(output).toContain('gemini-3.5-flash');
expect(output).not.toContain('gemini-3-flash\u0020'); // Avoid matching parts of substrings if not intended
expect(output).toMatchSnapshot();
});
it('renders role breakdown correctly under models', async () => {
const metrics = createTestMetrics({
models: {
@@ -24,7 +24,7 @@ import {
import { computeSessionStats } from '../utils/computeStats.js';
import { useSettings } from '../contexts/SettingsContext.js';
import type { QuotaStats } from '../types.js';
import { LlmRole } from '@google/gemini-cli-core';
import { LlmRole, getDisplayString } from '@google/gemini-cli-core';
// A more flexible and powerful StatRow component
interface StatRowProps {
@@ -101,7 +101,7 @@ const ModelUsageTable: React.FC<ModelUsageTableProps> = ({ models }) => {
Object.entries(models).forEach(([name, metrics]) => {
rows.push({
name,
displayName: name,
displayName: getDisplayString(name),
requests: metrics.api.totalRequests,
cachedTokens: metrics.tokens.cached.toLocaleString(),
inputTokens: metrics.tokens.prompt.toLocaleString(),
@@ -141,7 +141,7 @@ describe('ToolConfirmationQueue', () => {
expect(output).toContain('1 of 3');
expect(output).toContain('ls'); // Tool name
expect(output).toContain('list files'); // Tool description
expect(output).toContain('Allow execution of [ls]?');
expect(output).toContain('Allow execution of [Shell]?');
expect(output).toMatchSnapshot();
unmount();
@@ -84,6 +84,33 @@ exports[`AlternateBufferQuittingDisplay > renders with history but no pending it
Tips for getting started:
1. Create GEMINI.md files to customize your interactions
2. /help for more information
3. Ask coding questions, edit code or run commands
4. Be specific for the best results
╭──────────────────────────────────────────────────────────────────────────╮
│ ✓ tool1 Description for tool 1 │
│ │
╰──────────────────────────────────────────────────────────────────────────╯
╭──────────────────────────────────────────────────────────────────────────╮
│ ✓ tool2 Description for tool 2 │
│ │
╰──────────────────────────────────────────────────────────────────────────╯
"
`;
exports[`AlternateBufferQuittingDisplay > renders with pending items but no history > with_history_no_pending 1`] = `
"
▝▜▄ ▗█▀▀▜▙▝█▛▀▀▌▜██▖▟██▘▜█▘▜██▖▝█▛▝█▛
▝▜▄ █▌ █▙▟ ▐█▝█▛▐█ ▐█ ▐█▝█▖█▌ █▌
▗▟▀ ▜▙ ▝█▛ █▌▝ ▖▐█ ▐█ ▐█ ▐█ ▝██▌ █▌
▝▀ ▀▀▀▀▘▝▀▀▀▀▘▀▀▘ ▀▀▘▀▀▘▀▀▘ ▝▀▀▝▀▀
Gemini CLI v0.10.0
Tips for getting started:
1. Create GEMINI.md files to customize your interactions
2. /help for more information
@@ -123,6 +150,29 @@ Tips for getting started:
"
`;
exports[`AlternateBufferQuittingDisplay > renders with user and gemini messages > with_confirming_tool 1`] = `
"
▝▜▄ ▗█▀▀▜▙▝█▛▀▀▌▜██▖▟██▘▜█▘▜██▖▝█▛▝█▛
▝▜▄ █▌ █▙▟ ▐█▝█▛▐█ ▐█ ▐█▝█▖█▌ █▌
▗▟▀ ▜▙ ▝█▛ █▌▝ ▖▐█ ▐█ ▐█ ▐█ ▝██▌ █▌
▝▀ ▀▀▀▀▘▝▀▀▀▀▘▀▀▘ ▀▀▘▀▀▘▀▀▘ ▝▀▀▝▀▀
Gemini CLI v0.10.0
Tips for getting started:
1. Create GEMINI.md files to customize your interactions
2. /help for more information
3. Ask coding questions, edit code or run commands
4. Be specific for the best results
Action Required (was prompted):
? confirming_tool Confirming tool description
"
`;
exports[`AlternateBufferQuittingDisplay > renders with user and gemini messages > with_user_gemini_messages 1`] = `
"
▝▜▄ ▗█▀▀▜▙▝█▛▀▀▌▜██▖▟██▘▜█▘▜██▖▝█▛▝█▛
@@ -0,0 +1,20 @@
<svg xmlns="http://www.w3.org/2000/svg" width="920" height="88" viewBox="0 0 920 88">
<style>
text { font-family: Consolas, "Courier New", monospace; font-size: 14px; dominant-baseline: text-before-edge; white-space: pre; }
</style>
<rect width="920" height="88" fill="#000000" />
<g transform="translate(10, 10)">
<text x="0" y="2" fill="#333333" textLength="720" lengthAdjust="spacingAndGlyphs">╭──────────────────────────────────────────────────────────────────────────────╮</text>
<text x="0" y="19" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs"></text>
<text x="18" y="19" fill="#4796e4" textLength="9" lengthAdjust="spacingAndGlyphs">L</text>
<text x="27" y="19" fill="#6688d9" textLength="9" lengthAdjust="spacingAndGlyphs">i</text>
<text x="36" y="19" fill="#847ace" textLength="9" lengthAdjust="spacingAndGlyphs">n</text>
<text x="45" y="19" fill="#9974b4" textLength="9" lengthAdjust="spacingAndGlyphs">e</text>
<text x="63" y="19" fill="#c3677f" textLength="9" lengthAdjust="spacingAndGlyphs">1</text>
<text x="711" y="19" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs"></text>
<text x="0" y="36" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs"></text>
<text x="18" y="36" fill="#ffffff" textLength="54" lengthAdjust="spacingAndGlyphs">Line 2</text>
<text x="711" y="36" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs"></text>
<text x="0" y="53" fill="#333333" textLength="720" lengthAdjust="spacingAndGlyphs">╰──────────────────────────────────────────────────────────────────────────────╯</text>
</g>
</svg>

After

Width:  |  Height:  |  Size: 1.9 KiB

@@ -7,6 +7,13 @@ exports[`Banner > handles newlines in text 1`] = `
╰──────────────────────────────────────────────────────────────────────────────╯"
`;
exports[`Banner > handles newlines in text 2`] = `
"╭──────────────────────────────────────────────────────────────────────────────╮
│ Line 1 │
│ Line 2 │
╰──────────────────────────────────────────────────────────────────────────────╯"
`;
exports[`Banner > renders in info mode 1`] = `
"╭──────────────────────────────────────────────────────────────────────────────╮
│ Info Message │
@@ -11,6 +11,17 @@ exports[`<Checklist /> > renders expanded view correctly 1`] = `
"
`;
exports[`<Checklist /> > renders expanded view correctly 2`] = `
"────────────────────────────────────────────────────────────────────────────────────────────────────
Test List 1/3 completed (toggle me)
✓ Task 1
» Task 2
☐ Task 3
✗ Task 4
"
`;
exports[`<Checklist /> > renders summary view correctly (collapsed) 1`] = `
"────────────────────────────────────────────────────────────────────────────────────────────────────
Test List 1/3 completed (toggle me) » Task 2
@@ -5,6 +5,11 @@ exports[`<ContextSummaryDisplay /> > should not render empty parts 1`] = `
"
`;
exports[`<ContextSummaryDisplay /> > should not render empty parts 2`] = `
" 1 open file (F4 to view)
"
`;
exports[`<ContextSummaryDisplay /> > should render on a single line on a wide screen 1`] = `
" 1 open file (F4 to view) · 1 GEMINI.md file · 1 MCP server · 1 skill
"
@@ -0,0 +1,11 @@
<svg xmlns="http://www.w3.org/2000/svg" width="920" height="71" viewBox="0 0 920 71">
<style>
text { font-family: Consolas, "Courier New", monospace; font-size: 14px; dominant-baseline: text-before-edge; white-space: pre; }
</style>
<rect width="920" height="71" fill="#000000" />
<g transform="translate(10, 10)">
<text x="0" y="2" fill="#ffffff" textLength="900" lengthAdjust="spacingAndGlyphs">────────────────────────────────────────────────────────────────────────────────────────────────────</text>
<text x="0" y="19" fill="#ffffff" textLength="900" lengthAdjust="spacingAndGlyphs"> &gt; hello </text>
<text x="0" y="36" fill="#ffffff" textLength="900" lengthAdjust="spacingAndGlyphs">────────────────────────────────────────────────────────────────────────────────────────────────────</text>
</g>
</svg>

After

Width:  |  Height:  |  Size: 1.3 KiB

@@ -60,6 +60,12 @@ exports[`InputPrompt > Highlighting and Cursor Display > single-line scenarios >
────────────────────────────────────────────────────────────────────────────────────────────────────"
`;
exports[`InputPrompt > Highlighting and Cursor Display > single-line scenarios > should display cursor correctly 'at the end of the line' 2`] = `
"────────────────────────────────────────────────────────────────────────────────────────────────────
> hello
────────────────────────────────────────────────────────────────────────────────────────────────────"
`;
exports[`InputPrompt > Highlighting and Cursor Display > single-line scenarios > should display cursor correctly 'for multi-byte unicode characters' 1`] = `
"────────────────────────────────────────────────────────────────────────────────────────────────────
> hello 👍 world
@@ -168,6 +174,27 @@ exports[`InputPrompt > mouse interaction > should toggle paste expansion on doub
"
`;
exports[`InputPrompt > mouse interaction > should toggle paste expansion on double-click 4`] = `
"▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄
> [Pasted Text: 10 lines]
▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀
"
`;
exports[`InputPrompt > mouse interaction > should toggle paste expansion on double-click 5`] = `
"▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄
> [Pasted Text: 10 lines]
▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀
"
`;
exports[`InputPrompt > mouse interaction > should toggle paste expansion on double-click 6`] = `
"▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄
> [Pasted Text: 10 lines]
▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀
"
`;
exports[`InputPrompt > multiline rendering > should correctly render multiline input including blank lines 1`] = `
"────────────────────────────────────────────────────────────────────────────────────────────────────
> hello
@@ -1,5 +1,18 @@
// Vitest Snapshot v1, https://vitest.dev/guide/snapshot.html
exports[`LoopDetectionConfirmation > contains the expected options 1`] = `
" ╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ? A potential loop was detected │
│ │
│ This can happen due to repetitive tool calls or other model behavior. Do you want to keep loop │
│ detection enabled or disable it for this session? │
│ │
│ ● 1. Keep loop detection enabled (esc) │
│ 2. Disable loop detection for this session │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
"
`;
exports[`LoopDetectionConfirmation > renders correctly 1`] = `
" ╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ? A potential loop was detected │
@@ -215,3 +215,26 @@ exports[`<ModelStatsDisplay /> > should render "no API calls" message when there
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
"
`;
exports[`<ModelStatsDisplay /> > should resolve gemini-3-flash to gemini-3.5-flash via getDisplayString 1`] = `
"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
│ │
│ Model Stats For Nerds │
│ │
│ │
│ Metric gemini-3.5-flash │
│ ────────────────────────────────────────────────────────────────────────────────────────────── │
│ API │
│ Requests 1 │
│ Errors 0 (0.0%) │
│ Avg Latency 100ms │
│ Tokens │
│ Total 30 │
│ ↳ Input 5 │
│ ↳ Cache Reads 5 (50.0%) │
│ ↳ Thoughts 2 │
│ ↳ Tool 1 │
│ ↳ Output 20 │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
"
`;
@@ -16,6 +16,22 @@ exports[`ShortcutsHelp > renders correctly in 'narrow' mode on 'linux' 1`] = `
"
`;
exports[`ShortcutsHelp > renders correctly in 'narrow' mode on 'linux' 2`] = `
"────────────────────────────────────────
Shortcuts See /help for more
! shell mode
@ select file or folder
Double Esc clear & rewind
Tab focus UI
Ctrl+Y YOLO mode
Shift+Tab cycle mode
Ctrl+V paste images
Alt+M raw markdown mode
Ctrl+R reverse-search history
Ctrl+G open external editor
"
`;
exports[`ShortcutsHelp > renders correctly in 'narrow' mode on 'mac' 1`] = `
"────────────────────────────────────────
Shortcuts See /help for more
@@ -292,3 +292,30 @@ exports[`<StatsDisplay /> > renders role breakdown correctly under models 1`] =
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
"
`;
exports[`<StatsDisplay /> > resolves gemini-3-flash to gemini-3.5-flash in the model usage table 1`] = `
"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
│ │
│ Session Stats │
│ │
│ Interaction Summary │
│ Session ID: test-session-id │
│ Tool Calls: 0 ( ✓ 0 x 0 ) │
│ Success Rate: 0.0% │
│ │
│ Performance │
│ Wall Time: 1s │
│ Agent Active: 3.0s │
│ » API Time: 3.0s (100.0%) │
│ » Tool Time: 0s (0.0%) │
│ │
│ │
│ Model Usage │
│ Use /model to view model quota information │
│ │
│ Model Reqs Input Tokens Cache Reads Output Tokens │
│ ────────────────────────────────────────────────────────────────────────────────────────────── │
│ gemini-3.5-flash 5 2,000 500 3,000 │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
"
`;
@@ -25,6 +25,31 @@ exports[`Initial Theme Selection > should default to a dark theme when terminal
"
`;
exports[`Initial Theme Selection > should default to a dark theme when terminal background is dark and no theme is set 2`] = `
"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
│ │
│ > Select Theme Preview │
│ ▲ ┌─────────────────────────────────────────────────┐ │
│ 1. ANSI Dark │ │ │
│ 2. Atom One Dark │ 1 # function │ │
│ 3. Ayu Dark │ 2 def fibonacci(n): │ │
│ ● 4. Default Dark (Matches terminal) │ 3 a, b = 0, 1 │ │
│ 5. Dracula Dark │ 4 for _ in range(n): │ │
│ 6. GitHub Dark │ 5 a, b = b, a + b │ │
│ 7. GitHub Dark Colorblind Dark │ 6 return a │ │
│ 8. Holiday Dark │ │ │
│ 9. Shades Of Purple Dark │ 1 - print("Hello, " + name) │ │
│ 10. Solarized Dark │ 1 + print(f"Hello, {name}!") │ │
│ 11. Tokyo Night Dark │ │ │
│ 12. ANSI Light (Incompatible) └─────────────────────────────────────────────────┘ │
│ ▼ │
│ │
│ (Use Enter to select, Tab to configure scope, Esc to close) │
│ │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
"
`;
exports[`Initial Theme Selection > should default to a light theme when terminal background is light and no theme is set 1`] = `
"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
│ │
@@ -89,6 +114,20 @@ exports[`ThemeDialog Snapshots > should render correctly in scope selector mode
"
`;
exports[`ThemeDialog Snapshots > should render correctly in scope selector mode 2`] = `
"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
│ │
│ > Apply To │
│ ● 1. User Settings │
│ 2. Workspace Settings │
│ 3. System Settings │
│ │
│ (Use Enter to apply scope, Tab to select theme, Esc to close) │
│ │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
"
`;
exports[`ThemeDialog Snapshots > should render correctly in theme selection mode (isDevelopment: false) 1`] = `
"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
│ │
@@ -18,3 +18,12 @@ Tips for getting started:
3. Be specific for the best results
"
`;
exports[`Tips > 'renders fewer tips when GEMINI.md exi…' 2`] = `
"
Tips for getting started:
1. /help for more information
2. Ask coding questions, edit code or run commands
3. Be specific for the best results
"
`;
@@ -84,8 +84,8 @@
<text x="711" y="291" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs"></text>
<text x="0" y="308" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs"></text>
<text x="9" y="308" fill="#ffffff" textLength="180" lengthAdjust="spacingAndGlyphs"> Allow execution of </text>
<text x="189" y="308" fill="#ffffaf" textLength="54" lengthAdjust="spacingAndGlyphs" font-weight="bold">[echo]</text>
<text x="243" y="308" fill="#ffffff" textLength="468" lengthAdjust="spacingAndGlyphs">? </text>
<text x="189" y="308" fill="#ffffaf" textLength="63" lengthAdjust="spacingAndGlyphs" font-weight="bold">[Shell]</text>
<text x="252" y="308" fill="#ffffff" textLength="459" lengthAdjust="spacingAndGlyphs">? </text>
<text x="711" y="308" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs"></text>
<text x="0" y="325" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs"></text>
<text x="711" y="325" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs"></text>

Before

Width:  |  Height:  |  Size: 11 KiB

After

Width:  |  Height:  |  Size: 11 KiB

@@ -191,8 +191,8 @@
<text x="711" y="546" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs"></text>
<text x="0" y="563" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs"></text>
<text x="9" y="563" fill="#ffffff" textLength="180" lengthAdjust="spacingAndGlyphs"> Allow execution of </text>
<text x="189" y="563" fill="#ffffaf" textLength="54" lengthAdjust="spacingAndGlyphs" font-weight="bold">[echo]</text>
<text x="243" y="563" fill="#ffffff" textLength="468" lengthAdjust="spacingAndGlyphs">? </text>
<text x="189" y="563" fill="#ffffaf" textLength="63" lengthAdjust="spacingAndGlyphs" font-weight="bold">[Shell]</text>
<text x="252" y="563" fill="#ffffff" textLength="459" lengthAdjust="spacingAndGlyphs">? </text>
<text x="711" y="563" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs"></text>
<text x="0" y="580" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs"></text>
<text x="711" y="580" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs"></text>

Before

Width:  |  Height:  |  Size: 22 KiB

After

Width:  |  Height:  |  Size: 22 KiB

@@ -52,7 +52,7 @@ exports[`ToolConfirmationQueue > height allocation and layout > should handle se
│ Original: https://täst.com/ │
│ Actual Host (Punycode): https://xn--tst-qla.com/ │
│ │
│ Allow execution of [echo]?
│ Allow execution of [Shell]? │
│ │
│ ● 1. Allow once │
│ 2. Allow for this session │
@@ -138,7 +138,7 @@ exports[`ToolConfirmationQueue > height allocation and layout > should render th
│ │ echo "Line 49" │ │
│ │ echo "Line 50" │ │
│ ╰──────────────────────────────────────────────────────────────────────────╯ │
│ Allow execution of [echo]?
│ Allow execution of [Shell]? │
│ │
│ ● 1. Allow once │
│ 2. Allow for this session │
@@ -202,7 +202,7 @@ exports[`ToolConfirmationQueue > renders the confirming tool with progress indic
│ ╭──────────────────────────────────────────────────────────────────────────╮ │
│ │ ls │ │
│ ╰──────────────────────────────────────────────────────────────────────────╯ │
│ Allow execution of [ls]?
│ Allow execution of [Shell]?
│ │
│ ● 1. Allow once │
│ 2. Allow for this session │
@@ -41,6 +41,27 @@ exports[`<ToolStatsDisplay /> > should display stats for multiple tools correctl
"
`;
exports[`<ToolStatsDisplay /> > should display stats for multiple tools correctly 2`] = `
"╭────────────────────────────────────────────────────────────────────╮
│ │
│ Tool Stats For Nerds │
│ │
│ Tool Name Calls Success Rate Avg Duration │
│ ──────────────────────────────────────────────────────────────── │
│ tool-a 2 50.0% 100ms │
│ tool-b 1 100.0% 100ms │
│ │
│ User Decision Summary │
│ Total Reviewed Suggestions: 3 │
│ » Accepted: 1 │
│ » Rejected: 1 │
│ » Modified: 1 │
│ ──────────────────────────────────────────────────────────────── │
│ Overall Agreement Rate: 33.3% │
╰────────────────────────────────────────────────────────────────────╯
"
`;
exports[`<ToolStatsDisplay /> > should handle large values without wrapping or overlapping 1`] = `
"╭────────────────────────────────────────────────────────────────────╮
│ │
@@ -6,7 +6,11 @@
import { waitFor } from '../../../test-utils/async.js';
import { renderWithProviders } from '../../../test-utils/render.js';
import { SubagentGroupDisplay } from './SubagentGroupDisplay.js';
import { Kind, CoreToolCallStatus } from '@google/gemini-cli-core';
import {
Kind,
CoreToolCallStatus,
SubagentState,
} from '@google/gemini-cli-core';
import type { IndividualToolCallDisplay } from '../../types.js';
import { describe, it, expect, vi } from 'vitest';
import { Text } from 'ink';
@@ -27,12 +31,12 @@ describe('<SubagentGroupDisplay />', () => {
resultDisplay: {
isSubagentProgress: true,
agentName: 'api-monitor',
state: 'running',
state: SubagentState.RUNNING,
recentActivity: [
{
id: 'act-1',
type: 'tool_call',
status: 'running',
status: SubagentState.RUNNING,
content: '',
displayName: 'Action Required',
description: 'Verify server is running',
@@ -50,13 +54,13 @@ describe('<SubagentGroupDisplay />', () => {
resultDisplay: {
isSubagentProgress: true,
agentName: 'db-manager',
state: 'completed',
state: SubagentState.COMPLETED,
result: 'Database schema validated',
recentActivity: [
{
id: 'act-2',
type: 'thought',
status: 'completed',
status: SubagentState.COMPLETED,
content: 'Database schema validated',
},
],
@@ -13,6 +13,7 @@ import {
isSubagentProgress,
checkExhaustive,
type SubagentActivityItem,
SubagentState,
} from '@google/gemini-cli-core';
import {
SubagentProgressDisplay,
@@ -66,13 +67,13 @@ export const SubagentGroupDisplay: React.FC<SubagentGroupDisplayProps> = ({
const singleAgent = toolCalls[0].resultDisplay;
if (isSubagentProgress(singleAgent)) {
switch (singleAgent.state) {
case 'completed':
case SubagentState.COMPLETED:
headerText = 'Agent Completed';
break;
case 'cancelled':
case SubagentState.CANCELLED:
headerText = 'Agent Cancelled';
break;
case 'error':
case SubagentState.ERROR:
headerText = 'Agent Error';
break;
default:
@@ -88,8 +89,8 @@ export const SubagentGroupDisplay: React.FC<SubagentGroupDisplayProps> = ({
for (const tc of toolCalls) {
const progress = tc.resultDisplay;
if (isSubagentProgress(progress)) {
if (progress.state === 'completed') completedCount++;
else if (progress.state === 'running') runningCount++;
if (progress.state === SubagentState.COMPLETED) completedCount++;
else if (progress.state === SubagentState.RUNNING) runningCount++;
} else {
// It hasn't emitted progress yet, but it is "running"
runningCount++;
@@ -200,7 +201,7 @@ export const SubagentGroupDisplay: React.FC<SubagentGroupDisplayProps> = ({
let content = 'Starting...';
let formattedArgs: string | undefined;
if (progress.state === 'completed') {
if (progress.state === SubagentState.COMPLETED) {
if (
progress.terminateReason &&
progress.terminateReason !== 'GOAL'
@@ -223,18 +224,18 @@ export const SubagentGroupDisplay: React.FC<SubagentGroupDisplayProps> = ({
}
const displayArgs =
progress.state === 'completed' ? '' : formattedArgs;
progress.state === SubagentState.COMPLETED ? '' : formattedArgs;
const renderStatusIcon = () => {
const state = progress.state ?? 'running';
const state = progress.state ?? SubagentState.RUNNING;
switch (state) {
case 'running':
case SubagentState.RUNNING:
return <Text color={theme.text.primary}>!</Text>;
case 'completed':
case SubagentState.COMPLETED:
return <Text color={theme.status.success}></Text>;
case 'cancelled':
case SubagentState.CANCELLED:
return <Text color={theme.status.warning}></Text>;
case 'error':
case SubagentState.ERROR:
return <Text color={theme.status.error}></Text>;
default:
return checkExhaustive(state);
@@ -8,6 +8,7 @@ import { describe, it, expect } from 'vitest';
import { renderWithProviders } from '../../../test-utils/render.js';
import { SubagentHistoryMessage } from './SubagentHistoryMessage.js';
import type { HistoryItemSubagent } from '../../types.js';
import { SubagentState } from '@google/gemini-cli-core';
describe('SubagentHistoryMessage', () => {
const mockItem: HistoryItemSubagent = {
@@ -18,19 +19,19 @@ describe('SubagentHistoryMessage', () => {
id: '1',
type: 'thought',
content: 'Thinking about the problem',
status: 'completed',
status: SubagentState.COMPLETED,
},
{
id: '2',
type: 'tool_call',
content: 'Calling search_web',
status: 'running',
status: SubagentState.RUNNING,
},
{
id: '3',
type: 'tool_call',
content: 'Calling read_file fail',
status: 'error',
status: SubagentState.ERROR,
},
],
};
@@ -6,7 +6,7 @@
import { render, cleanup } from '../../../test-utils/render.js';
import { SubagentProgressDisplay } from './SubagentProgressDisplay.js';
import type { SubagentProgress } from '@google/gemini-cli-core';
import { type SubagentProgress, SubagentState } from '@google/gemini-cli-core';
import { describe, it, expect, vi, afterEach } from 'vitest';
describe('<SubagentProgressDisplay />', () => {
@@ -25,7 +25,7 @@ describe('<SubagentProgressDisplay />', () => {
type: 'tool_call',
content: 'run_shell_command',
args: '{"command": "echo hello", "description": "Say hello"}',
status: 'running',
status: SubagentState.RUNNING,
},
],
};
@@ -48,7 +48,7 @@ describe('<SubagentProgressDisplay />', () => {
displayName: 'RunShellCommand',
description: 'Executing echo hello',
args: '{"command": "echo hello"}',
status: 'running',
status: SubagentState.RUNNING,
},
],
};
@@ -69,7 +69,7 @@ describe('<SubagentProgressDisplay />', () => {
type: 'tool_call',
content: 'run_shell_command',
args: '{"command": "echo hello"}',
status: 'running',
status: SubagentState.RUNNING,
},
],
};
@@ -90,7 +90,7 @@ describe('<SubagentProgressDisplay />', () => {
type: 'tool_call',
content: 'write_file',
args: '{"file_path": "/tmp/test.txt", "content": "foo"}',
status: 'completed',
status: SubagentState.COMPLETED,
},
],
};
@@ -113,7 +113,7 @@ describe('<SubagentProgressDisplay />', () => {
type: 'tool_call',
content: 'run_shell_command',
args: JSON.stringify({ description: longDesc }),
status: 'running',
status: SubagentState.RUNNING,
},
],
};
@@ -133,7 +133,7 @@ describe('<SubagentProgressDisplay />', () => {
id: '5',
type: 'thought',
content: 'Thinking about life',
status: 'running',
status: SubagentState.RUNNING,
},
],
};
@@ -149,7 +149,7 @@ describe('<SubagentProgressDisplay />', () => {
isSubagentProgress: true,
agentName: 'TestAgent',
recentActivity: [],
state: 'cancelled',
state: SubagentState.CANCELLED,
};
const { lastFrame } = await render(
@@ -167,7 +167,7 @@ describe('<SubagentProgressDisplay />', () => {
id: '6',
type: 'thought',
content: 'Request cancelled.',
status: 'error',
status: SubagentState.ERROR,
},
],
};
@@ -188,7 +188,7 @@ describe('<SubagentProgressDisplay />', () => {
type: 'tool_call',
content: 'run_shell_command',
args: '{"command": "echo hello"}',
status: 'error',
status: SubagentState.ERROR,
},
],
};
@@ -9,9 +9,10 @@ import { Box, Text } from 'ink';
import { theme } from '../../semantic-colors.js';
import Spinner from 'ink-spinner';
import { MarkdownDisplay } from '../../utils/MarkdownDisplay.js';
import type {
SubagentProgress,
SubagentActivityItem,
import {
type SubagentProgress,
type SubagentActivityItem,
SubagentState,
} from '@google/gemini-cli-core';
import { TOOL_STATUS } from '../../constants.js';
import { STATUS_INDICATOR_WIDTH } from './ToolShared.js';
@@ -62,13 +63,13 @@ export const SubagentProgressDisplay: React.FC<
let headerText: string | undefined;
let headerColor = theme.text.secondary;
if (progress.state === 'cancelled') {
if (progress.state === SubagentState.CANCELLED) {
headerText = `Subagent ${progress.agentName} was cancelled.`;
headerColor = theme.status.warning;
} else if (progress.state === 'error') {
} else if (progress.state === SubagentState.ERROR) {
headerText = `Subagent ${progress.agentName} failed.`;
headerColor = theme.status.error;
} else if (progress.state === 'completed') {
} else if (progress.state === SubagentState.COMPLETED) {
headerText = `Subagent ${progress.agentName} completed.`;
headerColor = theme.status.success;
} else {
@@ -107,13 +108,13 @@ export const SubagentProgressDisplay: React.FC<
);
} else if (item.type === 'tool_call') {
const statusSymbol =
item.status === 'running' ? (
item.status === SubagentState.RUNNING ? (
<Spinner type="dots" />
) : item.status === 'completed' ? (
) : item.status === SubagentState.COMPLETED ? (
<Text color={theme.status.success}>
{TOOL_STATUS.SUCCESS}
</Text>
) : item.status === 'cancelled' ? (
) : item.status === SubagentState.CANCELLED ? (
<Text color={theme.status.warning} bold>
{TOOL_STATUS.CANCELED}
</Text>
@@ -135,7 +136,7 @@ export const SubagentProgressDisplay: React.FC<
<Text
bold
color={theme.text.primary}
strikethrough={item.status === 'cancelled'}
strikethrough={item.status === SubagentState.CANCELLED}
>
{item.displayName || item.content}
</Text>
@@ -144,7 +145,9 @@ export const SubagentProgressDisplay: React.FC<
<Text
color={theme.text.secondary}
wrap="truncate"
strikethrough={item.status === 'cancelled'}
strikethrough={
item.status === SubagentState.CANCELLED
}
>
{displayArgs}
</Text>
@@ -170,7 +173,7 @@ export const SubagentProgressDisplay: React.FC<
)}
<MarkdownDisplay
text={safeJsonToMarkdown(progress.result)}
isPending={progress.state !== 'completed'}
isPending={progress.state !== SubagentState.COMPLETED}
terminalWidth={terminalWidth}
/>
</Box>
@@ -275,6 +275,108 @@ describe('ToolConfirmationMessage', () => {
result.unmount();
});
it('should use the tool name for display in the confirmation question', async () => {
const confirmationDetails: SerializableConfirmationDetails = {
type: 'exec',
title: 'Confirm Execution',
command: '# This is a comment\necho "hello"',
rootCommand: 'echo',
rootCommands: ['echo'],
};
const { lastFrame, unmount } = await renderWithProviders(
<ToolConfirmationMessage
callId="test-call-id"
confirmationDetails={confirmationDetails}
config={mockConfig}
getPreferredEditor={vi.fn()}
availableTerminalHeight={30}
terminalWidth={80}
toolName="shell"
/>,
);
const output = lastFrame();
expect(output).toContain('Allow execution of [Shell]?');
unmount();
});
describe('tool name humanization', () => {
const cases = [
{
toolName: 'run_shell_command',
expected: 'Allow execution of [Shell]?',
desc: 'humanize run_shell_command to Shell',
},
{
toolName: 'shell',
expected: 'Allow execution of [Shell]?',
desc: 'humanize shell to Shell',
},
{
toolName: 'grep_search',
expected: 'Allow execution of [grep_search]?',
desc: 'keep raw name for non-shell tools',
},
];
for (const { toolName, expected, desc } of cases) {
it(`should ${desc}`, async () => {
const confirmationDetails: SerializableConfirmationDetails = {
type: 'exec',
title: 'Confirm',
command: 'ls',
rootCommand: 'ls',
rootCommands: ['ls'],
};
const { lastFrame, unmount } = await renderWithProviders(
<ToolConfirmationMessage
callId="test-call-id"
confirmationDetails={confirmationDetails}
config={mockConfig}
getPreferredEditor={vi.fn()}
availableTerminalHeight={30}
terminalWidth={80}
toolName={toolName}
/>,
);
expect(lastFrame()).toContain(expected);
unmount();
});
}
it('should humanize shell tool in sandbox expansion prompt', async () => {
const confirmationDetails: SerializableConfirmationDetails = {
type: 'sandbox_expansion',
title: 'Confirm',
command: 'ls',
rootCommand: 'ls',
additionalPermissions: {
network: true,
},
};
const { lastFrame, unmount } = await renderWithProviders(
<ToolConfirmationMessage
callId="test-call-id"
confirmationDetails={confirmationDetails}
config={mockConfig}
getPreferredEditor={vi.fn()}
availableTerminalHeight={30}
terminalWidth={80}
toolName="run_shell_command"
/>,
);
expect(lastFrame()).toContain(
'To run [Shell], allow access to the following?',
);
unmount();
});
});
describe('with folder trust', () => {
const editConfirmationDetails: SerializableConfirmationDetails = {
type: 'edit',
@@ -629,18 +629,13 @@ export const ToolConfirmationMessage: React.FC<
);
}
} else if (confirmationDetails.type === 'sandbox_expansion') {
const { additionalPermissions, command, rootCommand } =
confirmationDetails;
const { additionalPermissions, command } = confirmationDetails;
const readPaths = additionalPermissions?.fileSystem?.read || [];
const writePaths = additionalPermissions?.fileSystem?.write || [];
const network = additionalPermissions?.network;
const isShell = isShellTool(toolName);
const rootCmds = rootCommand
.split(',')
.map((c) => c.trim().split(/\s+/)[0])
.filter((c) => c && !c.startsWith('redirection'));
const commandNames = Array.from(new Set(rootCmds)).join(', ');
const commandNames = isShell ? 'Shell' : toolName;
question = '';
bodyContent = (
@@ -730,13 +725,7 @@ export const ToolConfirmationMessage: React.FC<
);
}
const commandNames = Array.from(
new Set(
commandsToDisplay
.map((cmd) => cmd.trim().split(/\s+/)[0])
.filter(Boolean),
),
).join(', ');
const commandNames = isShell ? 'Shell' : toolName;
const allowQuestion = (
<Text>
@@ -13,6 +13,7 @@ import {
ApprovalMode,
WRITE_FILE_DISPLAY_NAME,
Kind,
SubagentState,
} from '@google/gemini-cli-core';
import os from 'node:os';
import { createMockSettings } from '../../../test-utils/settings.js';
@@ -76,7 +77,7 @@ describe('ToolGroupMessage Regression Tests', () => {
resultDisplay: {
isSubagentProgress: true,
agentName: 'TestAgent',
state: 'running',
state: SubagentState.RUNNING,
recentActivity: [],
},
}),
@@ -112,7 +113,7 @@ describe('ToolGroupMessage Regression Tests', () => {
resultDisplay: {
isSubagentProgress: true,
agentName: 'TestAgent',
state: 'completed',
state: SubagentState.COMPLETED,
recentActivity: [],
},
}),
@@ -32,10 +32,12 @@ export const STATUS_INDICATOR_WIDTH = 3;
* Returns true if the tool name corresponds to a shell tool.
*/
export function isShellTool(name: string): boolean {
const normalized = name.toLowerCase();
return (
name === SHELL_COMMAND_NAME ||
name === SHELL_NAME ||
name === SHELL_TOOL_NAME
name === SHELL_TOOL_NAME ||
normalized === 'shell'
);
}
@@ -6,6 +6,12 @@ exports[`ErrorMessage > renders multiline error messages 1`] = `
"
`;
exports[`ErrorMessage > renders multiline error messages 2`] = `
"✕ Error line 1
Error line 2
"
`;
exports[`ErrorMessage > renders with the correct prefix and text 1`] = `
"✕ Something went wrong
"
@@ -16,6 +16,13 @@ exports[`<GeminiMessage /> - Raw Markdown Display Snapshots > renders pending st
"
`;
exports[`<GeminiMessage /> - Raw Markdown Display Snapshots > renders pending state with renderMarkdown=true 2`] = `
"✦ Test bold and code markdown
1 const x = 1;
"
`;
exports[`<GeminiMessage /> - Raw Markdown Display Snapshots > renders with renderMarkdown=false '(raw markdown with syntax highlightin…' 1`] = `
"✦ Test **bold** and \`code\` markdown
@@ -40,3 +47,12 @@ exports[`<GeminiMessage /> - Raw Markdown Display Snapshots > wraps long lines c
truncation
"
`;
exports[`<GeminiMessage /> - Raw Markdown Display Snapshots > wraps long lines correctly in raw markdown mode 2`] = `
"✦ This is a long
line that should
wrap correctly
without
truncation
"
`;
@@ -4,7 +4,7 @@ exports[`ToolConfirmationMessage Redirection > should display redirection warnin
"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
│ echo "hello" > test.txt │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
Allow execution of [echo]?
Allow execution of [Shell]?
Redirection detected. To auto-accept, press Shift+Tab
● 1. Allow once
@@ -133,7 +133,9 @@
<text x="63" y="546" fill="#cdcd00" textLength="81" lengthAdjust="spacingAndGlyphs">&quot;Line 50&quot;</text>
<text x="711" y="546" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs"></text>
<text x="0" y="563" fill="#333333" textLength="720" lengthAdjust="spacingAndGlyphs">╰──────────────────────────────────────────────────────────────────────────────╯</text>
<text x="0" y="580" fill="#ffffff" textLength="900" lengthAdjust="spacingAndGlyphs">Allow execution of [echo]? </text>
<text x="0" y="580" fill="#ffffff" textLength="171" lengthAdjust="spacingAndGlyphs">Allow execution of </text>
<text x="171" y="580" fill="#ffffaf" textLength="63" lengthAdjust="spacingAndGlyphs" font-weight="bold">[Shell]</text>
<text x="234" y="580" fill="#ffffff" textLength="666" lengthAdjust="spacingAndGlyphs">? </text>
<rect x="0" y="612" width="9" height="17" fill="#001a00" />
<text x="0" y="614" fill="#00cd00" textLength="9" lengthAdjust="spacingAndGlyphs"></text>
<rect x="9" y="612" width="9" height="17" fill="#001a00" />

Before

Width:  |  Height:  |  Size: 15 KiB

After

Width:  |  Height:  |  Size: 15 KiB

Some files were not shown because too many files have changed in this diff Show More