Observed 2026-10-03 by Claude Code: during a window of roughly 15-20 minutes, itemstore failed 6 times with only 'An error occurred invoking itemstore' no code, detail or request ID. Five failures were creates with 400-…
As title suggests, there should be a recent call, so agents know what happened recently when working with multiple agents.
Problem In about half of the Codex exec runs of one session the conderis MCP was either not loaded or answered 401 memoryrecall on an old project-memory endpoint. The agents then guessed: tried other endpoints or browse…
Problem Agent-ready tasks repeat the same project rules and build/compile checklist. When a rule changes e.g. '.meta files are git-ignored' became 'tracked', 41 task texts are outdated at once; the only fix is overridin…
Problem In a batch store, tags must be a comma-separated string; passing a JSON array fails the whole batch. Agents naturally send arrays. Proposal Accept both a string and an array of strings for tags single and batch,…
Problem Task content is capped at 4000 characters. Self-contained task briefs for autonomous agents goal, plan, edge cases, done-when, checklist with build commands and project rules regularly exceed that; a planner age…
Problem itemaction claim, complete, block and unblock require the item version, so every action needs a preceding itemget. In a coordinator workflow one agent reviewing and closing many subtasks done by other agents thi…
Observed 2026-09-26 in a Claude Code session outside of any project D:\tmp, no .agents/conderis.json. Steps 1. itemstorekind=memory, fields={...}, visibility=private without projectId - published as personal memory memo…
Anfrage: Prüfen, ob "Channels" Sinn ergeben – ein Chat, in den Agents schreiben können und gerade verbundene andere Agents die Nachricht im selben Moment bekommen. Alternative: ein MCP watch-Befehl. Erste Einschätzung K…
Decision 3 of 309: forcing a proposal works per call propose: true in itemstore, done in 315 and as a setting on the agent key in the web app. The key setting was split off from 315 on 2026-09-19 and runs after the swit…
Domain change from 309 Decision 1, split out of 315 so that the v2 tool surface 310 did not wait for it. Start with 309, section "Continue here". State today The itemstore description already lists visibility private, s…
Data model change from 309 Decision 6, split out of 315 so that the v2 tool surface 310 did not wait for a migration. v2 is live and maps version onto revisions internally; this task removes the revision tables. Start w…
Only memoryrecall maxChars, itemhistory limit and relationlist depth, limit let the caller size a response. The rest are fixed or unbounded: - tasklist has no limit internally 300 root tasks and returns every full descr…
Relations 287 connect tasks and memories only; the page says "Documentation pages are not part of the relation graph yet". A page cannot point at the task that caused it or the decision it explains, so its history and c…
A task is usually implemented over several commits, plus fixes and reviews. Record them so people in the web app and agents without a checkout can go from a task to its code: what changed, whether a half-done task has p…
Implement the concept in 290: terse summaries, memory weight, one level of submemories bags, a deterministic hygiene score and write-time feedback, so memory stays small and current in every project without one-off clea…
A single-operator service on shared hosting is a weak answer to "should I put my team's project knowledge here" — but concealing it is worse. Visitors will assume the least favourable version of anything left unsaid. Sa…
The intended model is that any GitHub source can reserve a repository and let agents work on it without adding users — valuable for open source, and a prompt-injection surface. Project instructions are delivered by memo…
Why this is separate 252 removed the lock upgrade that made concurrent creation deadlock. A retry policy was deliberately left out there, because it is a wider decision than that fix. What was measured Turning on Enable…
Outcome An authenticated agent can determine what it is allowed to do in a project without attempting a mutation and reading the resulting error. Problem The server derives effective permissions from AgentKey GranularPe…
Problem Hosted memorysearch takes only 30 results, KnowledgeService.List takes 100 before projection, and neither exposes a cursor or hasMore. The 2026-09-13 freshness audit needed multiple topic searches to inspect 62…
Requested after the WordsApp audit on 2026-09-13: historical pending-deployment reports, later successful deployments and dated DNS observations compete in recall. A current brief and reconciliation help, but the brief…
Observed during WordsApp memory maintenance on 2026-09-13: seven relationcreate calls using kind=supersedes from memory 34 to memories 1, 2, 6, 14, 17, 18 and 19 returned 'Relation saved.' Subsequent relationlist calls…
Corrected user intent All tasks remain attached to a project. This feature adds visibility, not personal/organization task scopes or standalone task namespaces. The earlier scope interpretation is superseded by this des…
Objective Preserve the option to earn revenue or sell the business while building adoption among users of multiple coding agents. The user sees 10,000 GitHub stars and a potential GitHub acquisition as an aspiration, no…
Concept v0: session closeout The active coding agent proposes at most a few durable findings after meaningful work: decision, gotcha or reusable note. Each proposal includes source evidence, project/scope, rationale, pr…
