Context Engineering Inside the Harness: 4 Mechanisms That Beat Context Overflow and Goal Loss on Long-Horizon Tasks
Survey of four harness mechanisms—context budgeting, compaction, todo-state, and memory—that keep long-horizon LLM agents on task across 200+ tool calls.
The article details how agent harnesses, not larger context windows, solve context overflow and goal loss on long-horizon tasks, citing Chroma's Context Rot report showing 18 LLMs (GPT-4.1, Claude 4, Gemini 2.5, Qwen3) degrade on long inputs. Concrete implementations include LangChain Deep Agents offloading tool responses over 20,000 tokens to the filesystem and truncating old tool calls at 85% window usage, and Claude Code capping auto memory at 25KB while re-reading the 5 most recently modified files after compaction. OpenAI's Responses API now offers server-side compaction via context_management with a standalone /responses/compact endpoint, which Codex uses for long-running coding tasks. Manus reports a roughly 100:1 input-to-output token ratio per ~50-tool-call task, motivating todo.md state recitation to prevent goal drift.
Attackers Exploit Critical Langflow and Rails Flaws in Credential
VulnCheck reports active exploitation of critical Langflow CVE-2026-0768 and Rails CVE-2026-66066 for credential harvesting, with detections rising to 360.
VulnCheck observed active exploitation of CVE-2026-0768 (CVSS 9.8) in Langflow and CVE-2026-66066 'KindaRails2Shell' (CVSS 9.5) in Ruby on Rails, with detections rising from 50 on August 30, 2026 to 360 by September 1. The Rails flaw allows unauthenticated arbitrary file reads, leaking secret_key_base, Rails master key, database passwords, cloud credentials and API tokens, ultimately enabling RCE; the patch still leaves the variation-key Marshal deserialization RCE gadget functional. Observed chains include a Python credential harvester with SimpleHelp remote access via CVE-2026-5027, and weaponization of CVE-2025-3248 to enlist hosts into an XMR mining botnet after disabling auditd. More than 7,100 exposed vulnerable Ruby on Rails instances and over 15,000 successful exploitation attempts across three Langflow flaws were recorded.
Product showcase: Doppler secures secrets for humans, pipelines, and AI agents
Doppler's secrets management platform centralizes credentials for engineers, CI/CD pipelines, MCP servers, and AI agents with runtime injection and dynamic secrets.
Doppler stores API keys, database URLs, tokens, and certificates in a single control plane and injects them at runtime, replacing .env files for human and machine identities including AI agents. It supports OIDC with short-lived identity tokens for Azure, AWS, and GCP, dynamic secrets scoped and time-boxed to single sessions, SCIM provisioning, 50+ integrations, and an MCP server that lets agents request configurations natively. Permissions are enforced at each layer so raw secrets stay out of logs, prompts, and model context, with versioning, rollback, SIEM log forwarding, and cloud or on-prem deployment.
Hacking Public Wi-Fi DNS to Steal Credentials
Attackers can hijack public Wi-Fi DNS to redirect users to credential-stealing fake login pages; commenters debate HTTPS limits and mitigations like encrypted DNS.
The discussion examines how an attacker controlling DNS on shared or public Wi-Fi networks can redirect requests for legitimate services to attacker-controlled servers to steal credentials. Commenters analyze whether HTTPS and certificates mitigate the attack, noting attackers often rely on HTTP or browser trust quirks. Suggested defenses include encrypted DNS (DoH), DNSSEC, and travel routers running OpenWRT. No specific campaign, victims, or indicators are provided.