Compare commits

..

4 Commits

Author SHA1 Message Date
8c71fbb9e5 fix: parse tagged local-model tool calls
All checks were successful
Codex Template Compliance / template-compliance (pull_request) Successful in 5s
Build / test-and-image (pull_request) Successful in 43s
2026-07-05 23:14:29 +02:00
578118ff50 Merge pull request 'docs: record DAVE presence timezone fallback' (#75) from codex/handoff-presence-timezone-fallback into codex/production-intelligence-terminal
All checks were successful
Release Dry Run / release-dry-run (push) Successful in 20s
Codex Template Compliance / template-compliance (push) Successful in 9s
Build / test-and-image (push) Successful in 32s
2026-07-05 21:07:25 +00:00
b3b8dc98af docs: record presence timezone fallback
All checks were successful
Codex Template Compliance / template-compliance (pull_request) Successful in 8s
Build / test-and-image (pull_request) Successful in 26s
2026-07-05 23:05:53 +02:00
f0a8162202 Merge pull request 'fix: fall back from invalid DAVE presence timezone' (#74) from codex/issue-73-presence-timezone-fallback into codex/production-intelligence-terminal
All checks were successful
Codex Template Compliance / template-compliance (push) Successful in 6s
Release Dry Run / release-dry-run (push) Successful in 16s
Build / test-and-image (push) Successful in 28s
2026-07-05 21:03:33 +00:00
3 changed files with 93 additions and 1 deletions

View File

@@ -14,6 +14,8 @@ Last updated: 2026-07-05
- PR runs 915-916 and production runs 917-919 passed, including unit tests, Compose validation, Docker build/publish, release dry-run, and template compliance. - PR runs 915-916 and production runs 917-919 passed, including unit tests, Compose validation, Docker build/publish, release dry-run, and template compliance.
- Dockge was updated from the Gitea Registry and explicitly configured with `DAVE_PRESENCE_ENABLED=true`, max 4 messages/day, 75-minute minimum gap, randomized 45-180 minute evaluation bounds, 60-minute post-interaction idle delay, and a 5-minute timer resolution. - Dockge was updated from the Gitea Registry and explicitly configured with `DAVE_PRESENCE_ENABLED=true`, max 4 messages/day, 75-minute minimum gap, randomized 45-180 minute evaluation bounds, 60-minute post-interaction idle delay, and a 5-minute timer resolution.
- Live `/api/health` reported `davePresence.enabled=true`, `running=true`, `dynamic=true`, `sentToday=0`, a variable `nextEvaluationAt`, the existing encrypted profile preserved, and no sweep error. The container reported `running/healthy`. - Live `/api/health` reported `davePresence.enabled=true`, `running=true`, `dynamic=true`, `sentToday=0`, a variable `nextEvaluationAt`, the existing encrypted profile preserved, and no sweep error. The container reported `running/healthy`.
- Live verification then exposed issue #73: an invalid optional profile timezone caused `lastReason=invalid_timezone`. PR #74 fixed runtime resolution to fall back to `DAVE_PRESENCE_TIMEZONE` without logging or modifying encrypted profile data. Merge commit: `f0a8162202bfe0a0a8ed2a00dc4f0f7092677eea`.
- PR runs 925-926 and production runs 927-929 passed. After redeployment and the startup timer, live health reported `lastReason=not_due` instead of `invalid_timezone`, with dynamic presence running, the profile preserved, the container healthy, and no sweep error.
## Latest Completed Work ## Latest Completed Work

View File

@@ -91,6 +91,10 @@ export class TerminalAgent {
const decision = parseDecision(response?.text); const decision = parseDecision(response?.text);
if (!decision) { if (!decision) {
const answer = String(response?.text || '').trim() || 'The agent returned no usable response.'; const answer = String(response?.text || '').trim() || 'The agent returned no usable response.';
if (looksLikeProtocolPayload(answer)) {
working += '\n\nPROTOCOL ERROR: The previous tool syntax was malformed. Return the documented JSON tool_call or final object only.';
continue;
}
this.lastTraceByChat.set(key, trace); this.lastTraceByChat.set(key, trace);
return { answer, trace }; return { answer, trace };
} }
@@ -272,6 +276,8 @@ Output exactly one JSON object without markdown:
function parseDecision(text) { function parseDecision(text) {
let value = String(text || '').trim().replace(/^```(?:json)?\s*/i, '').replace(/\s*```$/, ''); let value = String(text || '').trim().replace(/^```(?:json)?\s*/i, '').replace(/\s*```$/, '');
const tagged = parseTaggedToolCall(value);
if (tagged) return tagged;
const match = value.match(/\{[\s\S]*\}/); const match = value.match(/\{[\s\S]*\}/);
if (match) value = match[0]; if (match) value = match[0];
try { try {
@@ -282,9 +288,53 @@ function parseDecision(text) {
} }
} }
function parseTaggedToolCall(text) {
const callMatch = String(text || '').match(/<\|?tool_call\|?>\s*call:([a-z0-9_]+)\s*(\{[\s\S]*?\})\s*<(?:\/tool_call|tool_call\|)>/i);
if (callMatch) {
const argumentsValue = parseTaggedArguments(callMatch[2]);
if (argumentsValue) {
return {
type: 'tool_call',
tool: callMatch[1],
arguments: argumentsValue,
rationale: 'Model requested an allowlisted tool through tagged protocol.',
};
}
}
const jsonMatch = String(text || '').match(/<\|?tool_call\|?>\s*(\{[\s\S]*\})\s*<(?:\/tool_call|tool_call\|)>/i);
if (!jsonMatch) return null;
try {
const value = JSON.parse(jsonMatch[1]);
const tool = value.name || value.tool;
const args = value.arguments || value.parameters || {};
if (!/^[a-z0-9_]+$/i.test(String(tool || '')) || !args || Array.isArray(args) || typeof args !== 'object') return null;
return { type: 'tool_call', tool: String(tool), arguments: args, rationale: 'Model requested an allowlisted tool through tagged protocol.' };
} catch {
return null;
}
}
function parseTaggedArguments(value) {
const input = String(value || '').trim().slice(0, 4000);
try {
const parsed = JSON.parse(input);
return parsed && !Array.isArray(parsed) && typeof parsed === 'object' ? parsed : null;
} catch {
try {
const normalized = input.replace(/([{,]\s*)([a-z_][a-z0-9_]*)\s*:/gi, '$1"$2":');
const parsed = JSON.parse(normalized);
return parsed && !Array.isArray(parsed) && typeof parsed === 'object' ? parsed : null;
} catch {
return null;
}
}
}
function looksLikeProtocolPayload(text) { function looksLikeProtocolPayload(text) {
return /"?type"?\s*:\s*"?(?:tool_call|final)\b/i.test(text) return /"?type"?\s*:\s*"?(?:tool_call|final)\b/i.test(text)
|| /"?tool"?\s*:\s*"?[a-z0-9_]+/i.test(text); || /"?tool"?\s*:\s*"?[a-z0-9_]+/i.test(text)
|| /<\|?tool_call\|?>|<tool_call\|>|call:[a-z0-9_]+\s*\{/i.test(text);
} }
function finalizationFailureMessage(input) { function finalizationFailureMessage(input) {

View File

@@ -150,3 +150,43 @@ test('scheduled presence cannot create pending mutating actions', async () => {
assert.equal(result.trace[0].status, 'rejected'); assert.equal(result.trace[0].status, 'rejected');
assert.equal(executions, 0); assert.equal(executions, 0);
}); });
test('ChatML-style tagged tool calls are executed without leaking protocol text', async () => {
const calls = [];
let responseIndex = 0;
const responses = [
'<|tool_call>call:get_evidence{query:"Russia planned attack military escalation",limit:5}<tool_call|>',
JSON.stringify({ type: 'final', answer: 'The retrieved evidence does not confirm a specific planned attack.', confidence: 'medium', evidence: ['evt-russia'], notify: false, priority: 'routine' }),
];
const agent = new TerminalAgent({
provider: {
isConfigured: true,
async complete() { return { text: responses[responseIndex++] }; },
},
registry: new TerminalToolRegistry([{
name: 'get_evidence',
handler: async args => { calls.push(args); return [{ id: 'evt-russia' }]; },
}]),
});
const result = await agent.run('Wie sieht es mit dem angeblich geplanten Angriff von Russland aus?');
assert.deepEqual(calls, [{ query: 'Russia planned attack military escalation', limit: 5 }]);
assert.equal(result.trace[0].tool, 'get_evidence');
assert.doesNotMatch(result.answer, /tool_call|call:get_evidence/i);
});
test('malformed tagged protocol is repaired instead of returned to the user', async () => {
let responseIndex = 0;
const responses = [
'<|tool_call>call:get_evidence{broken arguments}<tool_call|>',
JSON.stringify({ type: 'final', answer: 'I could not run the malformed tool request.', confidence: 'low', evidence: [], notify: false, priority: 'routine' }),
];
const agent = new TerminalAgent({
provider: { isConfigured: true, async complete() { return { text: responses[responseIndex++] }; } },
registry: new TerminalToolRegistry([]),
});
const result = await agent.run('Check the claim');
assert.equal(result.answer, 'I could not run the malformed tool request.');
assert.doesNotMatch(result.answer, /tool_call|call:get_evidence/i);
});