fix/captures-root-citation
10 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
| 8108958a77 |
fix(decoder): mount the disassembly database, which it had lost
`SYLPHEED_DB=/xenia-rs/sylpheed.db` named a path that no longer exists. The xenia-rs repo was retired by the consolidation, its local clone was deleted, and the `/xenia-rs` mount that served the database was removed in #61 because it pointed at nothing. The env var stayed. So the decoder had NO database: `zq.py` and `/sylph-dis` -- most of what a static-RE brief asks for -- could not run. Mounted read-only at the container's repo root instead, which is where `zq.py` looks when `$SYLPHEED_DB` is unset, so there is no variable left to drift out of step with the mount. That drift is the whole bug: a path in an env var and a path in a mount, maintained separately. Read-only is deliberate. The host owns the file, DuckDB takes an exclusive lock to write, and two agents plus the human sharing one database would corrupt it. Regenerating means writing elsewhere and pointing $SYLPHEED_DB at it. Missing-file cases now say so and print the command that builds one, rather than starting an agent that discovers it mid-iteration. Verified in the real agent image: DB mounted, no env var set, `zq.py fn 0x824609C8` -> `Pak_FindEntryByName`, `zq.py classes` lists RTTI. The brief's tooling table also claimed the old path, and said nothing about the oracle binary; both corrected. It now records that the built Canary carries RE-INPUT/RE-DRAW but NOT the audit_61 branch probe -- measured with `strings` on both built binaries, zero hits; it is on two other branches (fork issue #1). Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
|||
| 46ee0d7f78 |
chore(agents): restore evidence sharing after the asset purge
Issue #49 removed game assets from git. It also, silently, removed the only transport agents had for showing each other evidence: each agent works in its OWN clone, so "commit the screenshot, the other one pulls it" was the mechanism, and PROTOCOL.md's file table said so in as many words -- "evidence cited by a finding -> git". That row sat directly above "🔴 Never commit game content", which is how 76 MB accumulated: the two contradicted each other and the table won, because it was the one that told you what to do. WHAT REPLACES IT * one host directory, `Sylpheed/docs/re/captures/`, bind-mounted read-write into BOTH agents at /work/docs/re/captures. All three -- host, decoder, port -- see the same files live, every citation resolves, and nothing can reach git history. Read-write on purpose: showing each other a screenshot is the point. * PROTOCOL.md's table rewritten. Cited evidence -> present but never committed; derived measurements (csv/tsv/txt/log/json) -> still git, they are our numbers not game content; evidence that must cross MACHINES -> attached to the issue or PR, because a bare clone has no captures. Verified, not assumed: container A wrote a .png there, a SEPARATE container B read it back, the host saw it, `git status` reported 0 changes, and `git check-ignore` named the rule. THE CHECKER WAS RED ON EVERY CLEAN CHECKOUT A fresh clone/worktree/CI has no captures, so it called all 134 citations dangling and exited 1. A gate that is red before anyone changes anything is one people learn to ignore -- the exact failure this file already carries a comment about. It now distinguishes "no captures here" (expected, explains itself, exit 0) from "these are missing" (real, exit 1, unchanged when assets ARE present). Both paths tested. ALSO * `sylph-decoder` no longer mounts `xenia-rs` -- retired repo, gone from disk, the mount pointed at nothing. * CONSOLIDATION.md closed: it still described captures as committed and the history fork as undecided. Both are settled. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
|||
| eccb789c0b |
docker: give each agent its own Gitea hands, and close the cross-approval hole
Phase 5 of docs/agents/GITEA-SETUP.md, plus a correction to Phase 2 that the runbook could not have known it needed. gitea-mcp v1.7.0 goes into both images, pinned by the sha256 the release publishes and smoke-tested with `--version` at build time, so a bad pin fails the build instead of the agent. Each entrypoint registers it at user scope for that container's own identity, remove-then-add so a restart is idempotent. The token is passed BY PATH. `-e GITEA_ACCESS_TOKEN=$(cat …)` would write it in cleartext into ~/.claude.json, which every session in the container reads; GITEA_ACCESS_TOKEN_FILE is new in the pinned version and leaves the secret in its read-only mount. Verified against the binary's own --help, not assumed. The tool filter stops being an experiment. The names are in the release README: each agent gets issues, notifications, labels, milestones and pull requests, and NOT `pull_request_review_write`. That one matters because separate identities open a hole the runbook did not name: Gitea refuses to let an author approve their own pull request, and does nothing about sylph-decoder approving sylph-port's. Two agents could satisfy `required_approvals = 1` between themselves and then merge, since branch protection blocks pushes to main and never blocked merges. Withholding the tool is defence in depth; the controls are in branch protection, and both docs now say so: approvals whitelisted to the human so an agent's approval does not count, merges whitelisted to the human so an approved PR is still merged by a person. Phase 2's check gains the step that actually tests it -- approve the throwaway PR yourself, then confirm the agent STILL has no merge button. Without that step, the check passes on an instance where the agents can merge each other's work. Also settles two entries on the runbook's own "not verified" list: the tool filter names, and the Gitea version (1.25.5, whose API schema carries enable_merge_whitelist and enable_approvals_whitelist under those names). Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01McNbzUeq1KRBWs4G6X2YVj |
|||
MechaCat02
|
1d1ffc5750 |
docker: stop the wrapper typing into live sessions, and support per-agent logins
Both agents stopped, and the decoder diagnosed it itself:
"I received '2' and '1' but I don't have a pending question those would
answer -- I was in the middle of setting up the /loop cron job."
claude-autonomous matched the BARE SUBSTRINGS 'Choose', 'trust' and 'accept' to
answer Claude Code's one-time first-run gates. The /loop prompt is echoed into
the terminal, and that day's briefs contain 'accepted as-is' and 'least
trustworthy' -- so expect matched the agent's OWN INSTRUCTIONS and typed 2\r and
1\r into a running session, which then sat waiting for a human to explain them.
The old comment argued a multi-word pattern 'never matches' because the gate
text wraps. True of a literal string, false of a whitespace-tolerant regex, which
is what these now are: \s+ spans the wrap, and the terminal is 200 columns wide.
Measured, old against new, against the real brief text and a real gate:
{accept} brief 0 gate 1 (case-sensitive; briefs say 'accepted')
{Yes,\s*I\s+accept} brief 0 gate 1
{trust} brief 1 <- the trigger
{Do\s+you\s+trust\s+the\s+files} brief 0
Two defences, because one is not enough for something that can type: patterns
prose cannot match, and gates skipped ENTIRELY on resume (SYLPH_SKIP_GATES) --
a resumed session cannot show a first-run gate, so there is nothing to answer
and everything to lose. Timeout cut 90s -> 25s for the same reason.
Also: SYLPH_OWN_LOGIN. Remote Control stopped registering under the long-lived
token, and the likely reason is scope -- `claude auth login` requests
user:sessions:claude_code and the token's auth status reports no email, org or
subscription. A per-agent `claude auth login` restores Remote Control AND avoids
the rotation collision, because each agent holds its own grant rather than a copy
of one. The flag stops the entrypoint seeding the host's credentials over it.
|
||
|
MechaCat02
|
b305aa4a5a |
docker: support a long-lived Claude token, and stop the seeding fighting it
The rotating OAuth credential file is why the agents kept parking, and a long-lived token removes the failure by construction instead of recovering from it after the fact. MEASURED 2026-09-04. ~/.claude/.credentials.json holds a refresh token that ROTATES ON USE. Seeding both containers from the host left three clients holding one token; the first to refresh invalidated the other two, and on the failed refresh Claude Code CLEARS the stored tokens -- writes empty strings, keeps the metadata, and parks at "Login expired". decoder credentials emptied 13:04:28 decoder last transcript 13:04:29 <- one second later The emptying and the park are the same event, which is why it never self-heals: not a stale token a retry could fix, but no token at all, with no browser in the container to complete /login. A hollow file passes every "does it exist" check -- 508 B healthy against 280 B emptied -- which is how three separate diagnoses missed it. And recovery re-armed the bug: after re-seeding, host and decoder held the IDENTICAL refresh token hash. `claude setup-token` issues a long-lived token against the same Claude subscription. Checked, not assumed: `claude auth login` defaults to --claudeai and it is `--console` that means Console/API billing, so this is not the separate API bill. `CLAUDE_CODE_OAUTH_TOKEN` is recognised by the installed binary. Passed as an ENVIRONMENT VARIABLE, both halves of the failure are gone: nothing rotates, so peers cannot invalidate each other, and there is no file for Claude Code to empty on a failure. Both launchers read $HOME/.sylph-claude-token if present -- same pattern as SYLPH_GIT_CREDENTIALS -- and both entrypoints skip OAuth seeding entirely when the variable is set, because copying the rotating file in would re-create the exact collision the token exists to remove. Inert until the file exists. Without it, nothing changes. Also worth recording for the preflight work: `claude auth status` prints JSON with loggedIn/authMethod/subscriptionType. That is a far better SessionStart assertion than checking a file exists, and it would have caught this on the first iteration rather than the third incident. |
||
|
MechaCat02
|
4ac23b94dd |
docker: auto-restart, and resume the session the agent was actually in
The decoder died mid-task and it took four separate findings to explain, each of which read as something else: 1. OOM-KILLED, REPORTED AS A CLEAN EXIT. `OOMKilled: true` with **ExitCode 0**. So `--restart on-failure` would treat a memory kill as a successful finish and leave the agent down -- the policy has to be `unless-stopped`. 2. THE JOB CAP WAS SET AND THEN REMOVED THREE LINES LATER. build-reborn has always exported CARGO_BUILD_JOBS, but a raw `cargo test --release -p sylpheed-formats` never reaches the wrapper. Adding `-e CARGO_BUILD_JOBS` to the launcher did not help either: the entrypoint recomputes and exports over it unconditionally. An explicit value now wins, and says so in the log. 3. THE MEMORY CONSTANT WAS WRONG. `mem_gib * 2 / 3` assumes ~1.5 GB per job; release rustc on this workspace needs ~2 GB, and 4 jobs in 6 GB is what died. Divisor is now 2. 4. `--continue` CANNOT RESUME AN ABRUPT DEATH, which is the only kind we get. It resolves through ~/.claude.json's per-project `history`/`lastSessionId`, and MEASURED mid-session both are None -- they are written at a graceful shutdown. A killed container never writes them, so `--continue` answered "No conversation found to continue" with 33 MB of transcripts in the volume beside it. Persisting .claude.json did not help, because the fields were never populated in the first place; that attempt is removed rather than left in looking useful. The TRANSCRIPTS are durable and named by session id, so the entrypoint reads the id off the newest one for its cwd and passes `--resume <id>`. Verified on both agents: each reattached to its exact prior session and appended to the same file rather than opening a new one. The /loop prompt is still passed alongside `--resume`, so the loop is RE-ARMED rather than merely restored -- a resumed conversation with no wake-up scheduled answers once and stops, which looks like resuming and is not. Restarting into the same death is guarded at the other end: a start less than 120 s after the previous one begins FRESH instead of continuing back into whatever killed it. That fired correctly during this work. On resume the agent is told it was restarted, that its in-progress work is uncommitted in the tree, that any build or capture it had running did not finish and its absence is not a result, and which wrapper to prefer over a raw release build. |
||
|
MechaCat02
|
d2d2592c92 |
decoder: mount the disassembly DB and the flat VA image
The decoder had neither, and reported the gap precisely: four scripts in this repo READ /work/xenia-rs/sylpheed.db and nothing produces it, so the whole static PPC route was consumers with the producer missing. Both exist on the host and are now mounted read-only: the 586 MB database (25 481 functions, 851 classes with RTTI, EH tables, imports, 1.8M indirect-dispatch candidates) and the decompressed image. The image is the more useful of the two. It is a FLAT VA DUMP -- file offset = VA - 0x82000000 -- so reading a known address needs no XEX decrypt, no LZX, and no booted emulator. The decoder had independently recovered the same bytes by dumping /dev/shm/xenia_memory_* and validating against the GamePart table, which is good work and a sound method, but it noted itself that needing a running emulator is a bad dependency for something the entire static corpus rests on. It does not need one. Also recorded that an earlier claim the .pe was STALE was tested and refuted, so nobody re-litigates it, and that instructions.raw is an INT rather than hex. Written down as reference material, explicitly NOT a deliverable: they are read-only, they come from outside the repository, and a fresh checkout elsewhere has neither. Reimplementing the producer belongs in sylpheed-formats, and until it exists every static finding rests on an artefact this project cannot rebuild. |
||
|
MechaCat02
|
5a9b75e152 |
agents: they never spoke, the decoder lost the disc, and both shared one state dir
Three defects, all mine, found by checking instead of assuming. **They never exchanged a word.** SendMessage=0, ListAgents=0 across both new sessions. PROTOCOL.md specified in detail what a message MAY and MAY NOT do and never said how to send one or that the other agent was addressable -- they knew that last time only because the human told them directly, and rebuilding with fresh volumes wiped it. Policy without mechanism is prose. Now documented with the two addresses, a worked example, and an instruction to introduce themselves on the first iteration rather than waiting to have a question. **The decoder lost the disc and the ISO.** They used to arrive inside the project mount and silently stopped when /work became a clone. Silently is the word: the disc-gated tests SELF-SKIP without SYLPHEED_DISC and report green, so a whole test suite would have passed while measuring nothing. Both are now mounted explicitly, the ISO at a stable path so run-canary does not depend on host directory names. **Both agents shared one Claude state directory.** They share the host's ~/.claude, and once both working directories became /work they resolved to the same projects/-work/ -- two supposedly independent agents writing to one place, which undoes the point of separate checkouts. Each now has its own volume, seeded once from the host with credentials only, so a token refresh writes locally and neither can corrupt the host's auth. Also widened the pacing rule. It banned ScheduleWakeup by name; the decoder then scheduled itself an hourly cron job -- not harmful, but the same instinct that ended a run yesterday, through a door I had left open. Now: no self-scheduling by any route. Mount audit after the changes: shared and intentional are the exchange volume and the read-only credential seed. Everything else -- repo, Claude state, cargo, target, canary, disc, ISO -- is per agent or one-sided. |
||
|
MechaCat02
|
824b150be4 |
containers: fix volume ownership and make the clone guard survive interruption
Two bugs, both mine, both found by starting the thing.
**Volume mount points must exist AND be owned by the agent before USER agent.**
Docker seeds a named volume from whatever the image has at that path, ownership
included, and creates a ROOT-OWNED directory when the path is absent. Either way
the agent cannot write, and the failure surfaced far from its cause: "clone
FAILED", with no permission error anywhere in sight. The port's own Dockerfile
already carried a comment explaining this trap, which I then walked into for
/work and /exchange.
**The clone guard checked for a .git directory, not a usable HEAD.** A clone
interrupted partway -- the container was removed while one ran -- leaves a .git
with no commits, and a presence check then skips the retry forever and hands the
agent an empty repository that looks like a checkout. It now verifies HEAD, and
clones via a temp directory so a partial result never lands in /work at all.
Also: the port launcher's path defaults still assumed the old repo root, so it
mounted no disc; and the stale /reborn notice is gone now that there is one
repository.
Verified running: both agents cloned
|
||
|
MechaCat02
|
c58196b795 |
containers: each agent clones the monorepo into its own volume
The last structural fix for the collision class that has bitten three times. Both containers now clone the repository into their OWN named volume instead of bind-mounting a human's working tree, so an agent's local git config cannot capture a human's commits, a credential helper cannot leak a container-only path onto the host, and a `git add -A` cannot sweep another party's in-flight files. Cloned once at startup and never auto-pulled: pulling under a running agent moves files out from under whatever it is mid-edit, which is the same bug again. Accepted knowingly: Claude Code keys per-project memory off the working directory, so moving off the host path starts that memory empty. The corpus in docs/ is the memory that matters and it travels with the clone. Other changes: * docker/agent -> docker/decoder; the launcher is sylph-decoder. Roles, not "the agent", now that there is more than one. * /reborn is gone -- one repository now, so the port reads HANDOFF from its own checkout rather than through a live read-only mount of someone else's tree. * Canary mounts separately at /canary; it stays a fork tracking upstream. * A shared `sylpheed-exchange` volume at /exchange, with tools/ on PATH so `share` is available in both. * The decoder's credential file gets the .host-copy treatment the port already had -- `credential.helper=store` rewrites by rename-over-target, which is EBUSY on a bind mount and reports a fatal that is not one. * Budget split deliberately: decoder 5 cpu / 6 GB, port 3 / 4, leaving room for the planned Referee. "Half the host" was right when there was one agent. Prompts move to docs/agents/ and are rewritten around the protocol: the oracle is the running game, dynamic RE stays with the decoder, each iteration must attempt to refute one claim of the other, and neither may verify its way out of its own role. |
