{"content": "rerun of four load-sensitive tests behind the shared lock came back - lockf -k\u2026", "meta": {"from": "journal"}} {"content": "the await tag does this in one step \u2014 [!await] makes the rest of the turn what you wait for; [!await on=(\"\", \"helper:\")] waits on those; it runs only when it opens the last text of your turn", "meta": {"from": "journal"}} {"content": "Four helpers were stopped at 00:55 and again resumed; until the cause is found: never run pkill or killall with a pattern; stop only processes you started yourself, by their exact pid.", "meta": {"from": "main"}} {"content": "One more for your a-f job, after your batches: to-do 2643 (journal todo read 2643), a check that runs out of time says so, in features/checks.", "meta": {"from": "main"}} {"content": "rerun of four load-sensitive tests came back - lockf -k\u2026", "meta": {"from": "journal"}} {"content": "fact 27 \u2014 Running src/journal.py against the live .journal root starts a\u2026 \u2014 Seen 2026-10-01: with VERSION bumped in the tree, src/journal.py --root .journal saw the live server as another build and started a new one on a new port (8431, 8432), and the user's tabs kept losing connection. Run source builds against a throwaway or demo root (~/projects/demo-crumb/.journal), never the live one, until the release is installed.", "meta": {"from": "journal"}} {"content": "fact 20 \u2014 A slim supervisor holds the agent and a worker reloads on every build \u2014 Since 2.118.0 (2026-09-23). src/supervisor.py is standard library only and never reloads: journal claude hands its process over to it (os.execv), and it owns the pty and the agent process, relays the terminal, writes the printed and screen captures, listens on the typist socket, restarts the agent in the same session from a relaunch command written to its runtime folder while a restart is pending, and stops it with escalation while draining the pty (an agent cannot finish exiting on macOS while its output is unread). It starts the worker (src/worker.py, which runs runner/worker.py; engine/worker.py stays as an alias for supervisors started before 2.201) and starts it again whenever it exits: RELOAD on a new build, RELAUNCH to restart the agent, STOP to end, HEAL or a quick crash to roll back a build through journal heal. The worker holds everything else: seating the session, the start-up confirm typed through the typist, services, viewer, update check, check-in, and the one-time relaunch of sessions launched before agents/terminal.py LAUNCH. agents/terminal.py holds only journal-side helpers. The server (serve.py) still runs the engines and re-execs itself on a .py change. When the agent exits, the supervisor runs journal ended, which puts set-aside hooks back and stops the server when no session is left.; fact 24 \u2014 An answer followed by tool calls can be missing from Claude's\u2026 \u2014 Seen 2026-09-24 for messages 9391-9404: text blocks opening with [!reply:n] that were followed by tool calls never appeared in the session's jsonl (only thinking and tool_use rows did), so the journal never saw them and the replies were lost. When a turn goes on after answering, send the answer with journal message reply \"\" instead of the tag.; rule 38 \u2014 Never change the git branch until the user says so, by name \u2014 The work happens on the branch the user named. That was main until message 5929 and question 80 (2026-09-23), which moved the sins work to the branch sins. Do not create, switch to or merge any other branch unless the user names it in their own words.; rule 46 \u2014 Only commit and push once the whole journal is proven to boot \u2014 Messages 2178 and 2179. A release that has not been started for real can crash every project that installs it, as 2.78.3 did for Codex and 2.84.0 did to project records. Before every commit and push: the full suite passes, including tests/test_it_boots.py, which installs a packed copy into a fresh project, launches Claude and Codex from it, writes a project record, upgrades again and checks the record survives. When a change touches launching, installing or upgrading, also start a real journal in a scratch project and close it properly afterwards, leaving no process behind.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 24 judged files since th\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 24 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "law L5 \u2014 Every subagent dispatch names the agent - a human name, a little\u2026 \u2014 A name is how the user and the chat tell subagents apart and how they are messaged later; an id or a task line is not a name. Start the dispatch's description with the name, a colon, then the task, such as \"Dr. Einstein: profile the slow hooks\" or \"Coco Rams: draw the plan card\". A designer can borrow from famous designers, a researcher from famous scientists, mixed up for fun.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 `base.py`, changed since the last check, breaks a rule. Fix\u2026 \u2014 Code Commandments \u2014 `base.py`, changed since the last check, breaks a rule. Fix it now, at its SOURCE, while the code is still in front of you: \u00b7 \u2022 python-mutable-value-object at /Users/jessegall/projects/agent-journal/.claude/worktrees/main-ada-branchley/src/resources/base.py:147 \u00b7 LOAD the skill `commandments-python-value-objects` before fixing \u2014 load it even if you believe you already have. \u00b7 Run `commandments info ` if a rule is not one you recognise. This check reads a file at a time, so it is not the whole picture \u2014 `judge` still is.", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "fact 18 \u2014 cProfile inflates the slow-request profiles about tenfold \u2014 The faults feature writes a profile when a request passes its budget, and the profile is taken with cProfile, which adds per-call overhead. On 2026-09-22 /api/summary profiled at 58ms with 48ms inside Resource.fork's deep copy; with the profiler off the same call ran in 2 to 7ms. Read the profile for where the time goes in relative terms, then time the call with curl before changing anything.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 37 judged files since t\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 37 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; work 1 is still open \u2014 end it or park it before you stop: journal work end 1 --how \"\", or journal work park 1 \"\"", "meta": {"from": "journal"}} {"content": "feature tests for B9-B12 and the check timeout came back - cd\u2026", "meta": {"from": "journal"}} {"content": "full suite on B9-B12 and the check timeout came back - python3\u2026", "meta": {"from": "journal"}} {"content": "law L3 \u2014 Read narrowly - grep for the line, sed a range, head the file; never\u2026 \u2014 Everything a tool returns stays in the context for good and is paid for on every turn after it. Search before you read, read the range you need, and cap output with grep, head or tail. Read a whole file only when you need all of it.", "meta": {"from": "journal"}} {"content": "work 1 is still open \u2014 end it or park it before you stop: journal work end 1 --how \"\", or journal work park 1 \"\"", "meta": {"from": "journal"}} {"content": "sharing, phone and every-action rerun came back - cd\u2026", "meta": {"from": "journal"}} {"content": "fact 25 \u2014 A designer's install packs the whole tree, half-done server edits\u2026 \u2014 2026-09-25: Eames and Saul run python3 src/journal.py --root .journal upgrade after their viewer builds; it packs every file in src, so a server handler I was halfway through writing went live and raised on every PostToolUse hook. While designers work in parallel, keep server edits whole between tool calls (write and test in the scratchpad first), and reinstall after reverting anything.; rule 37 \u2014 Close every to-do explicitly with todo done or a Journal commit\u2026 \u2014 Ending work does not close its row. A to-do is closed by journal todo done --how, or by a commit whose message carries Journal: todos done at column 0, several numbers separated by commas. A row left open after its work landed misleads the next session and auto mode.; rule 39 \u2014 Use only registered exclamation response tags \u2014 A tag like [!reply:12] runs a command, and only the tags in the tags.runs setting are registered. An invented tag does nothing and shows as raw text in the chat. Use the registered ones (reply, log, end, todo, fact, rule) and nothing else.; rule 51 \u2014 Every finished feature is committed, pushed and released with a new\u2026 \u2014 Message 9207 (2026-09-24): when a new feature is ready, commit, push and publish a new tag. This is the user's standing word for releasing, so rule 44's only-when-the-user-says is met by it for finished features; fixes in between wait for the next feature or a patch the user asks for.; rule 54 \u2014 Settings and feature switches are read at boot and on change, never\u2026 \u2014 The user, message 13349: the application boots, determines every feature and setting once, and re-evaluates only when something changes, such as a setting or a plugin. Never lazy-load settings.", "meta": {"from": "journal"}} {"content": "rule 57 \u2014 Never merge the overnight refactor into main before its pull request\u2026 \u2014 Messages 15005, 15006, 15109, 15110 (2026-10-04): all refactor work goes on branch overnight-refactor and reaches the user as one pull request, which they read in the morning; nothing of it is merged into main until they say so. Hotfixes the user explicitly asks for go to main at once and are merged into the branch.", "meta": {"from": "journal"}} {"content": "final full suite on the rebased tip came back - cd\u2026", "meta": {"from": "journal"}} {"content": "fact 13 \u2014 This live session runs the installed copy in .journal/journal.pyz \u2014 The running journal (server, hooks, CLI) runs from .journal/journal.pyz with its viewer and skills in .journal/src, never from the repo. A change in the repo reaches it only through python3 src/journal.py --root .journal upgrade, which packs the zip again. A commit alone changes nothing that is running.; rule 50 \u2014 Everything the user does is doable in the viewer \u2014 Message 6710 (2026-09-23): the user never uses the CLI, only the UI; everything should be doable from the viewer. The journal commands are for agents; any action meant for the user (making boards, confirming, accepting, hosting, watching an agent) needs its place in the viewer.", "meta": {"from": "journal"}} {"content": "your chat talked about the journal's workings - \"to-do 2643 are done\" \u2014 the user sees replies, reactions, pills and reads themselves; say what the work is instead; install.py names 2 files in the project \u2014 write the path so the chat can link it: install.py, src/install.py", "meta": {"from": "journal"}} {"content": "While your commits are in review: please rebase helper-main-ada-branchley onto overnight-refactor now (it has gained Hedy's g-p, Barbara's providers, Edsger's engine/HTTP and Alan's q-z work). Expect conflicts in features/base.py (register_always now takes a dict key from both Hedy and Alan), engine/ports.py and engine/git (Alan moved sharing's probes into engine/ports.py; your engine/git.py stays), and checks (Alan moved MarkTestRuns into checks). Keep your migration as m0062 (Alan's is m0063). Run the suite behind the lock, then report the new tip.", "meta": {"from": "main"}} {"content": "rule 36 \u2014 Clean, DRY, idiomatic before it is committed, never after it is\u2026 \u2014 The user should never be the one who finds duplication, dead code, a clumsy name or a pattern the codebase does not use. Read the diff before every commit as a reviewer would, and fix what is not clean then, not in a follow-up after a complaint.", "meta": {"from": "journal"}} {"content": "launch.py names 3 files in the project \u2014 write the path so the chat can link it: src/agents/launch.py, src/features/agent_sessions/launch.py, src/features/auto_update/launch.py", "meta": {"from": "journal"}} {"content": "fact 9 \u2014 Every public method on a controller becomes a journal command \u2014 The CLI is generated from the controllers: each public method of Controller, or of a typed controller, turns into journal . A helper added to the base class therefore becomes a command on every type \u2014 which is how journal handled and journal refuse came to exist, from the CRUD funnel and the refusal funnel. An internal helper on a controller is named with a leading underscore, as _shaped and _status already are, or it ships as a command nobody meant.", "meta": {"from": "journal"}} {"content": "fact 23 \u2014 Every upgrade brings system sequences and their triggers in line\u2026 \u2014 install.py runs ship_sequences after the migrations on each upgrade, so features/sequences/shipped.py is the whole source: change its wording and the next upgrade updates every journal, no migration needed. Shipped rows carry system=True and are read-only for everyone but SYSTEM (controllers/base.py _shipped).; that Bash call returned 53,089 characters, the largest this session \u2014 It stays in the context for good. If you were looking for one thing in it, the next read can be narrower: grep for the line, sed a range, head the file.", "meta": {"from": "journal"}} {"content": "rule 56 \u2014 Helpers are for work that writes; subagents read, research and design \u2014 The user, message 13464: there must be a clear distinction. A subagent can be dispatched for anything read-only: research, review, design. A helper is for actual work that writes, best in its own worktree when the work is separate. Dieter designing in Claude Design should have been a subagent, not a helper.", "meta": {"from": "journal"}} {"content": "rule 35 \u2014 Write clean code - one funnel per kind of operation, never the same\u2026 \u2014 Every kind of operation has one funnel: one method that creates, one that saves, one that refuses, one that formats. A second method that does the same thing under another name splits the behaviour, and the two drift apart. Before writing a method, search for the one that already does it and extend that. scripts/checks/funnels.py finds bodies written twice.; rule 42 \u2014 Every user-facing text passes the formatters before it leaves the\u2026 \u2014 Not only a brief. A title, an abstract, an outcome and every section body are read by a person, so each goes through the same formatters on its way to the viewer \u2014 chat turns, activity items, to-do rows, inspector pages, docs alike. One field formatted out of five is not a rule, it is an accident, and it is how a raw tag ended up in the activity list after the tags feature had been stripping them for weeks. When a new field carries words a person reads, it joins the list in the same place.; rule 43 \u2014 A request or hook over its budget is fixed before the next release \u2014 Comment 1151 on this rule. When the faults feature reports a request, a hook or a command slower than its budget, file it as a to-do at once. It does not jump ahead of the work in hand, but no version is published while one is still open: profile it, fix it, and verify the new time before the release goes out. The budget is 50ms, because everything runs locally against files.; rule 27 \u2014 Name a declaration with the word a reader already knows \u2014 An attribute, a variable or a field gets the ordinary programming word for what it holds, not an evocative one. was, heard and alone were poetry; aliases, notify_actions and urgent_actions are what they are. The test: could a reader who has never seen this codebase guess what it holds from the name alone? Prose belongs in the help text and the abstract, where it is read as prose. This does not license abbreviations \u2014 a plain word in full, not a short one.", "meta": {"from": "journal"}} {"content": "work 2 in hand \u2014 Rebase the a-f refactor onto overnight-refactor \u2014 if this is not what you are doing, end it or park it and start the work you are in", "meta": {"from": "journal"}} {"content": "rule 48 \u2014 The viewer is built from its component library, and pages only\u2026 \u2014 Message 4258. Every visual piece the viewer shows more than once, or that a user would recognise as the same kind of thing (a dialog, a side panel or inspector, a dropdown, a list row, a switch, a button), is one component in web/src/kit, extracted aggressively, and every page composes those components instead of building its own copy. Before writing markup or styles in a page, look for the kit component that already does it and extend it with a prop; a second hand-built version is a bug. The side panel that animated in but not out, while a separate skill panel did both, is the example.", "meta": {"from": "journal"}} {"content": "rule 41 \u2014 Keep moving, run the whole suite before every commit, never wait \u2014 The full suite runs in about seven seconds: .venv/bin/python -m pytest -q --timeout=300 -n auto. Run it before every commit instead of picking tests by name. Group rows that sit in the same code into one sitting: write them all, test once, commit once. And never wait, not for a subagent, a build, or an answer you can carry on without. Dispatch it and keep working. If you truly are waiting on something, say so in the work log.", "meta": {"from": "journal"}} {"content": "the log tag does this in one step \u2014 [!log:N] makes the turn itself the log entry; it runs only when it opens the last text of your turn", "meta": {"from": "journal"}} {"content": "full suite on the rebased tip came back\u2026", "meta": {"from": "journal"}} {"content": "full suite after the phone/feed.py rename fix came back\u2026", "meta": {"from": "journal"}} {"content": "rule 55 \u2014 Always dispatch Codex helpers on gpt-6-sol \u2014 The user's word, message 13431: switch the codex agents to GPT-6-Sol and make it their default. ~/.codex/config.toml names it as the default model too.", "meta": {"from": "journal"}} {"content": "Taken: your twelve commits are on overnight-refactor (3390679d). Thank you. The review of them is still out; if it finds anything it comes back to you. Next, same worktree: the parts of to-do 2650 that stay inside features a-f (B3.9 open works for a to-do as a Works method only if it stays small, B6.6 dumps: Refused for invalid input, _refuse only for forcible rules, B9.4 lost()/repaired() and the upgrade_mark unlink into install.py, B10.5 told_uses vs Context.every, Feature.plural's last caller). Edsger is changing every controller lightly (an @action marker, controllers by class), so rebase often. Commit per item, report.", "meta": {"from": "main"}} {"content": "Code Commandments \u2014 `controller.py`, changed since the last check, breaks a rul\u2026 \u2014 Code Commandments \u2014 `controller.py`, changed since the last check, breaks a rule. Fix it now, at its SOURCE, while the code is still in front of you: \u00b7 \u2022 python-raise-without-cause at /Users/jessegall/projects/agent-journal/.claude/worktrees/main-ada-branchley/src/features/dumps/controller.py:81 \u00b7 LOAD the skill `commandments-python-exceptions` before fixing \u2014 load it even if you believe you already have. \u00b7 Run `commandments info ` if a rule is not one you recognise. This check reads a file at a time, so it is not the whole picture \u2014 `judge` still is.", "meta": {"from": "journal"}} {"content": "law L1 \u2014 Every subagent dispatch names its model and chooses the least\u2026 \u2014 Use a fast, economical model for mechanical work with a known answer, a capable general model for careful implementation, and the strongest model only when the task turns on difficult judgement. Inheriting the orchestrator's model is not a model choice. If the dispatch API cannot accept a model, that operation is exempt.; a link you gave in the chat is not pinned; if the user will come back to it\u2026 \u2014 https://www.anthropic.com/legal/aup - journal notice create \"\" --set link=\"https://www.anthropic.com/legal/aup\" --set label=\"\" --set tone=note; a link you gave in the chat is not pinned; if the user will come back to it\u2026 \u2014 https://support.claude.com/en/articles/8106465 - journal notice create \"\" --set link=\"https://support.claude.com/en/articles/8106465\" --set label=\"\" --set tone=note", "meta": {"from": "journal"}} {"content": "Quick check: where are you, and is anything stuck (a rebase conflict, the suite lock)? Commit what is done now, even partly, rebase onto overnight-refactor, and report; the rest can follow. The branch goes to the user in the morning.", "meta": {"from": "main"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 3 judged files since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 3 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; fact 24 \u2014 An answer followed by tool calls can be missing from Claude's\u2026 \u2014 Seen 2026-09-24 for messages 9391-9404: text blocks opening with [!reply:n] that were followed by tool calls never appeared in the session's jsonl (only thinking and tool_use rows did), so the journal never saw them and the replies were lost. When a turn goes on after answering, send the answer with journal message reply \"\" instead of the tag.; rule 46 \u2014 Only commit and push once the whole journal is proven to boot \u2014 Messages 2178 and 2179. A release that has not been started for real can crash every project that installs it, as 2.78.3 did for Codex and 2.84.0 did to project records. Before every commit and push: the full suite passes, including tests/test_it_boots.py, which installs a packed copy into a fresh project, launches Claude and Codex from it, writes a project record, upgrades again and checks the record survives. When a change touches launching, installing or upgrading, also start a real journal in a scratch project and close it properly afterwards, leaving no process behind.", "meta": {"from": "journal"}} {"content": "the await tag does this in one step \u2014 [!await] makes the rest of the turn what you wait for; [!await on=(\"\", \"helper:\")] waits on those; it runs only when it opens the last text of your turn", "meta": {"from": "journal"}} {"content": "full suite on the two committed 2650 items came back - .venv/bin/python -m\u2026", "meta": {"from": "journal"}} {"content": "work 3 is still open \u2014 end it or park it before you stop: journal work end 3 --how \"\", or journal work park 3 \"\"; rule 38 \u2014 Never change the git branch until the user says so, by name \u2014 The work happens on the branch the user named. That was main until message 5929 and question 80 (2026-09-23), which moved the sins work to the branch sins. Do not create, switch to or merge any other branch unless the user names it in their own words.", "meta": {"from": "journal"}} {"content": "Taken (both). Thank you, Ada. Finish the three small ones if you can within the next hour (B10.5 told_uses vs Context.every, Feature.plural's last caller, and B9.4 only if it stays safe), then report; if B9.4 is risky, leave it filed.", "meta": {"from": "main"}} {"content": "rule 45 \u2014 No prose words as names in code - said, says, heard, spoke, told\u2026 \u2014 Messages 1360 and 1698. The user has said more than once that code must not read like prose: a variable, attribute, property or function is named for what it holds or does (text, command, labels, lines), never with a verb from a story. 'says' on the Design type (1360) and 'said = call.said.lower()' in features/recital.py (1698) are the examples. Rule 27 states the naming rule; this one carries the words, so writing one of them whispers it. Before writing a name, ask whether a reader who has never seen the code would know what it holds.", "meta": {"from": "journal"}} {"content": "A late review of your first twelve commits found one fix needed before the user reads the PR, plus small points: to-do 2670 (journal todo read 2670). Most important: engine/proc.py streamed() must start the shell in its own session and kill the whole process group on timeout, or the new check timeout cannot stop a test run. Do that first, with the claim inside _ran and the m0062 double-write guard; the idiom points after. Rebase, commit, suite behind the lock, report.", "meta": {"from": "main"}} {"content": "your command ran 30s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 32s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "commandments-python-absence, commandments-python-exceptions changed since you\u2026 \u2014 load one again when you next need it; only the every-start skills are held for", "meta": {"from": "journal"}}