Skip to content

fix(#8626)!: pin the CLI binaries and their node on the trusted PATH - #8633

Merged
waynesun09 merged 2 commits into
mainfrom
agent/8626-pin-cli-trusted-path
Oct 20, 2026
Merged

waynesun09 merged 2 commits into
mainfrom
agent/8626-pin-cli-trusted-path

Conversation

@fullsend-ai-coder

Copy link
Copy Markdown
Contributor

Summary

The claude, codex, pi and OpenCode launches now pin their CLI by the same rule the loader's python3 has followed since #8591. The CLI must come from FULLSEND_TRUSTED_PATH, and neither its resolved file nor any directory above it may be writable or owned by the agent user. pi's CLI and codex's npm launcher are #!/usr/bin/env node scripts, so the launch now starts them through a node pinned by the same rule. Before, env looked node up on the PATH left after .env was read.

Breaking change: a custom sandbox image whose CLI, or whose node for a node-script CLI, is found only through an agent-writable PATH directory, or through a symlink into one, now fails the launch with exit 127.

Related Issue

Follows #8575 and #8591; sequenced after #8605 (merged).

Changes

  • internal/runtime/env_data.go
    • envDataBinaryPin generalises the python3 lookup to any executable name: trusted-PATH search, "$FULLSEND_READLINK" -f with PATH="$FULLSEND_TRUSTED_PATH", a writable-ancestor walk on the resolved path, the first match as root, and exit 127 with fullsend: <name> not found in a PATH directory the agent cannot write.
    • envDataTrustedPin records FULLSEND_TRUSTED_PATH and a new read-only FULLSEND_READLINK once per launch. FULLSEND_READLINK is added to the shared drop list.
    • envDataLoad now pins only python3, because the launch's CLI pin has already recorded the trusted PATH and a second readonly aborts dash. EnvDataLoad, the codex harness-env probe and the OpenCode trusted-env probe have no CLI pin, so they run envDataTrustedPin first.
  • internal/runtime/binary_pin.go
    • binaryPin(varName, nodeVar, binary) = trusted pin + CLI pin + nodeShebangPin.
    • nodeShebangPin reads the pinned CLI's first line with the read builtin. On an exact #!/usr/bin/env node it pins node by the same rule; otherwise the node pin is empty.
    • cliLaunch emits ${NODE:+"$NODE"} "$CLI". The PATH the CLI inherits is unchanged.
  • claude, codex, pi and OpenCode use the shared pin and launch form. Each adds a FULLSEND_<RUNTIME>_NODE pin to its .env drop names. OpenCode's own openCodeBinaryPin now uses binaryPin.
  • Codex goldens regenerated (go test ./internal/runtime/ -run TestCodexGolden -update).
  • Docs: docs/runtimes/{claude,codex,pi,opencode}.md state that the CLI, and node for node-script CLIs, must sit in a PATH directory the sandbox user cannot write. The pin descriptions in docs/contributing/runtime-implementation.md and docs/guides/dev/cli-internals.md are updated to match.

Testing

  • New binary_pin_test.go, run under /bin/sh and dash as a non-root user, for all four CLIs:
    • an agent-writable CLI earlier on PATH is not pinned, and the protected one is pinned as its resolved path and launched;
    • with only an agent-writable CLI, or a protected symlink into an agent-writable directory, the launch exits 127 with the new message;
    • for a node-script CLI, an agent-writable node earlier on PATH, or one put first by a later PATH change, never runs. The protected node starts the CLI, and with only an agent-writable node the launch exits 127;
    • the node pin is read-only.
  • Mutation check: replacing the trusted-PATH iteration with command -v fails all 24 subtests of the three lookup tests.
  • Existing launch tests that run stub CLIs from t.TempDir() mark those directories protected through a test shell function (protectedDirsShell), the technique env_data_test.go already uses. TestBuildRunCommand_ClaudeMissingExits127 no longer depends on the host's /usr/bin; it failed on main in this sandbox because a real claude is installed there.
  • go test ./internal/runtime/ passes. Patch coverage is 100% for every changed function.
  • Smoke-ran the real pins in the sandbox image as the non-root user. The agent-owned /sandbox/.venv/bin is skipped, claude and opencode resolve to ELF binaries with no node, and codex and pi resolve to their node scripts with /usr/bin/node.
  • make lint: pre-commit run could not fetch its remote hook repositories here (TLS failure). The local hooks (gofmt, go vet, broken symlinks, docs links, lychee) and the pre-commit-hooks v6.0.0 hooks were run directly and passed; gitleaks was covered by scan-secrets.
  • These failures happen identically on main in this sandbox (network and port tests), so they are unrelated: internal/cli TestStartFetchService_* and TestPostScriptEnv_*, internal/fetch and internal/security.

Notes for reviewers

  • Not changed: the pi Agent tool's child binary (piBin) is still resolved at Bootstrap with command -v pi (pi_bootstrap.go). It is not one of the launch pins the issue lists; it may deserve a follow-up.
  • Each preflight (codex --version and the others) still runs the bare CLI name at Bootstrap, before any agent iteration.

Checklist

  • PR title follows Conventional Commits, with ! for a breaking change and a BREAKING CHANGE: trailer in the commit
  • No DCO sign-off: this is an autonomous agent commit

🤖 Generated with Claude Code


Closes #8626

Post-script verification

  • Branch is not main/master (agent/8626-pin-cli-trusted-path)
  • Secret scan passed (gitleaks — bbe0ab242efec0f433ae6b744f0ba9c16293988c..HEAD)
  • PR body secret scan passed (gitleaks — no-git)

The claude, codex, pi and OpenCode launches found their CLI with a bare
`command -v` on the launch PATH. A sandbox image can put a directory
the agent user owns first on PATH, so the launch could start a CLI the
agent planted there. pi's CLI and codex's npm launcher start with
`#!/usr/bin/env node`, so their node was looked up on whatever PATH the
launch shell had after .env was read.

Since #8591 the loader's python3 follows a stricter rule, and the CLI
pins now follow it too:

- envDataBinaryPin generalises the python3 lookup. It takes the first
  name on FULLSEND_TRUSTED_PATH, resolves it with the pinned readlink,
  walks the resolved path for agent-writable or agent-owned ancestors,
  and pins the resolved path read-only. With none it exits 127 with
  "fullsend: <cli> not found in a PATH directory the agent cannot
  write". As root it takes the first match.
- envDataTrustedPin records FULLSEND_TRUSTED_PATH and a new read-only
  FULLSEND_READLINK once per launch. binaryPin runs it before the CLI
  pin, and envDataLoad now pins only python3, so no launch runs a
  second `readonly` of the same name (which aborts dash). EnvDataLoad
  and the codex and OpenCode env-read probes, which have no CLI pin,
  run envDataTrustedPin themselves.
- binaryPin reads the pinned CLI's first line with the `read` builtin.
  For `#!/usr/bin/env node` it pins node by the same rule, and the
  launch runs `"$NODE" "$CLI"` (cliLaunch); otherwise the node pin is
  empty and the CLI starts as before. The PATH the CLI and its tools
  inherit is unchanged. The new FULLSEND_<RUNTIME>_NODE pins are on
  each launch's .env drop list, like the other pins.

Tests run the pins under /bin/sh and dash as a non-root user. An
agent-writable CLI or node earlier on PATH is not pinned, a protected
symlink into an agent-writable directory is refused, and with no
qualifying file the launch exits 127. Replacing the trusted-PATH
lookup with `command -v` fails all 24 of those subtests. Existing
launch tests mark their stub directories protected through a `test`
shell function, as env_data_test.go already does. The codex goldens
are regenerated. The runtime docs state the new requirement.

Note: `pre-commit run` could not fetch its remote hook repositories
in the sandbox (TLS failure). The local hooks (gofmt, go vet,
broken-symlinks, docs-links, lychee) and the pre-commit-hooks v6.0.0
hooks were run directly and passed. gitleaks was covered by
scan-secrets.

BREAKING CHANGE: a custom sandbox image whose claude, codex, pi or
opencode CLI, or the node that runs a `#!/usr/bin/env node` CLI, is
found only through a PATH directory the sandbox user owns or can write
(or through a symlink into one) now fails the launch with exit 127.
Install the CLI and node in a directory the sandbox user cannot write.

Closes #8626

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
@fullsend-ai-review

Copy link
Copy Markdown

🤖 Review · ⚠️ Cancelled · Ended 7:19 PM UTC

Commit: 540deae · View workflow run →

@fullsend-ai-review

fullsend-ai-review Bot commented Oct 20, 2026 •

Copy link
Copy Markdown

🤖 Finished Review · ✅ Success · Started 7:21 PM UTC · Completed 7:40 PM UTC

Commit: 540deae · View workflow run →

Runtime: pi · Model: sonnet → claude-sonnet-5-5 · Effort: high · Cost: $3.39

@github-actions

github-actions Bot commented Oct 20, 2026 •

Copy link
Copy Markdown

Site preview

Preview: https://071e64b0-site.fullsend-ai.workers.dev

Commit: 50ef6254a72e803f4780990bf7727ab177052f8e

@codecov

codecov Bot commented Oct 20, 2026

Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

@waynesun09

Copy link
Copy Markdown
Member

/fs-fix-stop

@github-actions github-actions Bot added the fullsend-no-fix Skip bot-triggered fix agent runs label Oct 20, 2026
@github-actions

Copy link
Copy Markdown

Fix agent disabled for this PR. Remove the fullsend-no-fix label or use /fs-fix to re-engage.

@fullsend-ai-review fullsend-ai-review Bot added the risk/moderate PR risk: moderate label Oct 20, 2026
@fullsend-ai-review

fullsend-ai-review Bot commented Oct 20, 2026 •

Copy link
Copy Markdown

<!-- fullsend:risk-assessment -->
Risk Assessment: moderate (2/5)

Details

Moderate risk change driven by elevated runtime churn and a flagged breaking change for custom images, mitigated by bot authorship, zero protected paths, solid test coverage, and close scope alignment with linked issue #8626.

Previous run

<!-- fullsend:risk-assessment -->
Risk Assessment: moderate (2/5)

Details

Moderate risk change driven by elevated runtime churn and a flagged breaking change for custom images, mitigated by bot authorship, zero protected paths, solid test coverage, and close scope alignment with linked issue #8626.

@fullsend-ai-review

fullsend-ai-review Bot commented Oct 20, 2026 •

Copy link
Copy Markdown

Review

Findings

Low

  • [injection-vuln] internal/runtime/binary_pin.go:44 — nodeShebangPin discards the status of the read redirect, so a pinned CLI that is executable but unreadable by the sandbox user falls through to an empty node pin and is launched directly. If it were a #!/usr/bin/env node script, env would resolve node on the post-.env PATH. The new #!*/env arms close the readable-shebang bypass from the prior review. The remaining case is hard to reach: the pinned file and every ancestor must be neither writable nor owned by the agent user, and an unreadable node script cannot run under node in any working image. Defense-in-depth only.
    Remediation: Refuse the launch (exit 127) when the pinned CLI cannot be opened for inspection, distinguishing an open failure from read returning nonzero at EOF, and add a non-root test with an executable but unreadable env-node script and an attacker-controlled PATH.
  • [stale-doc] docs/contributing/runtime-implementation.md:1013 — The Agent tool contract bullet still says "the manifest names the binary children run". After this PR, children start through the pinned pi and node exported as FULLSEND_PI_CHILD_BIN and FULLSEND_PI_CHILD_NODE, and fullsend-agent.js no longer reads piBin. The manifest table at line 986 already says so.
    Remediation: Drop "the binary children run" from the list at line 1013, or point to FULLSEND_PI_CHILD_BIN / FULLSEND_PI_CHILD_NODE.

Earlier findings

  • f_70f5a519efda3cf2 — reclassified (medium → low): the new env-shebang case arms in binary_pin.go:44-47 close the readable-shebang bypass. Only the unreadable-CLI case remains, listed above.
  • f_238e0c4748ce800a — resolved_by_change: docs/contributing/runtime-implementation.md:1349-1350 now says the CLI pin (binaryPin, through envDataTrustedPin) records FULLSEND_TRUSTED_PATH.
Previous run

<!-- fullsend:review-findings-v2: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 -->

Review

Findings

Medium

  • [injection-vuln] internal/runtime/binary_pin.go:41 — nodeShebangPin pins node only when the CLI's first line, read with IFS= read -r, is exactly #!/usr/bin/env node. Other shebangs that also look node up on PATH (trailing whitespace or CR, #! /usr/bin/env node, #!/usr/bin/env -S node) fall into the (*) readonly nodeVar= branch. The CLI then runs directly, and env resolves node on the post-.env, potentially agent-writable PATH. The CLI file itself stays protected, and the gap matters only for a custom image whose root-owned CLI uses a non-standard env-node shebang. The CLIs this PR targets (pi, npm's codex launcher) use the exact form, and issue Pin the CLI binaries and their node interpreter on the trusted PATH #8626 specifies the exact match, so this is a fail-open edge in the new hardening, not a bypass of the default configuration.
    Remediation: Either fail closed (exit 127 with a clear message) when the first line is a #! shebang that runs /usr/bin/env but is not the supported exact form, or normalize equivalent env-node forms (trailing whitespace/CR, #! spacing) before matching. Add non-root /bin/sh tests for these variants asserting that an agent-writable node never runs.
  • [stale-doc] docs/contributing/runtime-implementation.md:1349 — The Codex PATH-pinning paragraph still says FULLSEND_TRUSTED_PATH is recorded read-only before .env by envDataLoad. After this PR, envDataLoad no longer records it. binaryPin (via envDataTrustedPin) records it once per launch, and the probes record it through EnvDataLoad.
    Remediation: Reword line 1349 to say FULLSEND_TRUSTED_PATH is recorded read-only before .env by the launch's CLI pin (binaryPin/envDataTrustedPin), or by EnvDataLoad for the probes, instead of by envDataLoad.

Low

  • [doc-style] docs/runtimes/claude.md:258 — Line 258 is 128 characters long. The PR spliced its new sentence onto the existing paragraph without rewrapping, which goes against the ~80-column prose-wrapping rule in docs/contributing/documentation.md for paragraphs you are already editing.
    Remediation: Wrap the paragraph at word boundaries close to 80 columns.

Labels: Go changes to the sandbox launch pinning (CLI and node trusted-PATH hardening).


Next steps:

  • /fs-fix — agent addresses review findings automatically
  • /fs-fix <your instruction> — agent fixes with your specific guidance
  • Push commits directly — review re-runs automatically on push
  • /fs-fix-stop — disable automatic fix runs for this PR

fullsend-ai-review[bot]

This comment was marked as outdated.

fullsend-ai-review[bot]

This comment was marked as outdated.

@fullsend-ai-review fullsend-ai-review Bot added go Pull requests that update go code component/sandbox OpenShell sandbox environment security Security threat model and related concerns labels Oct 20, 2026
…other env shebangs

The Agent tool started each child as the manifest's piBin. pi's CLI is a
`#!/usr/bin/env node` script, so env looked node up on the PATH the
parent inherited after .env. The launch now exports the pi and node it
pinned before .env (FULLSEND_PI_CHILD_BIN, FULLSEND_PI_CHILD_NODE, both
on the loader's drop list), and fullsend-agent.js starts children with
them, starting none when either is missing or not absolute.

nodeShebangPin pinned node only for an exact `#!/usr/bin/env node` line;
any other line that starts the CLI through env (`#! /usr/bin/env node`,
`env -S node`, a trailing space or CR, another program) ran the CLI with
env resolving its interpreter on the post-.env PATH. Those now stop the
launch with exit 127.

Docs: the trusted-PATH paragraph names the CLI pin as its recorder, the
readlink failure mode is described as it now shows up, and claude.md's
edited paragraph is rewrapped.

Assisted-by: Claude (fix), Codex (review)
Signed-off-by: Wayne Sun <gsun@redhat.com>
@fullsend-ai-review

fullsend-ai-review Bot commented Oct 20, 2026 •

Copy link
Copy Markdown

🤖 Finished Review · ✅ Success · Started 7:47 PM UTC · Completed 7:59 PM UTC

Commit: 50ef625 · View workflow run →

Runtime: pi · Model: sonnet → claude-sonnet-5-5 · Effort: high · Cost: $3.35

@fullsend-ai-review fullsend-ai-review Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Note: The following review comments could not be posted on the diff (GitHub returned 422) and are included here instead:

  • docs/contributing/runtime-implementation.md (file-level): Line 1013 ·
    [low] stale-doc

The Agent tool contract bullet still says 'the manifest names the binary children run'. After this PR, children start through the pinned pi and node exported as FULLSEND_PI_CHILD_BIN and FULLSEND_PI_CHILD_NODE, and fullsend-agent.js no longer reads piBin. The manifest table at line 986 already says so. The rest of the rationale (extension list, tool allowlists, usage file) still holds.

Suggested fix: Drop 'the binary children run' from the list at line 1013, or point to FULLSEND_PI_CHILD_BIN / FULLSEND_PI_CHILD_NODE as the source of the child binary.

Comment thread internal/runtime/binary_pin.go Resolved
@fullsend-ai-review fullsend-ai-review Bot added the ready-for-merge All reviewers approved — ready to merge label Oct 20, 2026

@waynesun09 waynesun09 left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Validated in the sandbox image as the sandbox user with a node and each CLI planted first on PATH: claude, codex, pi and opencode start from root-owned paths, pi and codex through /usr/bin/node, and pi sub-agents through the same pinned pair. Go suite passes under dash, JS suite passes.

@waynesun09
waynesun09 added this pull request to the merge queue Oct 20, 2026
@github-merge-queue
github-merge-queue Bot removed this pull request from the merge queue due to failed status checks Oct 20, 2026
@waynesun09
waynesun09 added this pull request to the merge queue Oct 20, 2026
Merged via the queue into main with commit d93007f Oct 20, 2026
92 checks passed
@waynesun09
waynesun09 deleted the agent/8626-pin-cli-trusted-path branch October 20, 2026 21:15
jctanner added a commit to jctanner-fullsend-ai/fullsend that referenced this pull request Oct 23, 2026
Retroactive record of the decision implemented in PR fullsend-ai#8605 (merged
2026-10-20), extended by fullsend-ai#8589 (pi) and fullsend-ai#8633 (CLI binary pinning).
Hook scripts resolve their interpreter and PATH only from directories
the agent cannot write.

Restructured per review feedback: Decision states the rules a safe
hook setup must follow (trusted location, hooks see only trusted
locations, one resolver, protected to the point of use, no hook no
tool call, every runtime, no untrusted fallback, nothing protectable
means fail closed), with a per-runtime conformance table. Factual
corrections: the shared resolver is hookPreflightInterpreter, the
Claude PATH is baked into hooks.json at Bootstrap (not exported at
launch), Codex hook children use FULLSEND_TRUSTED_PATH (not
FULLSEND_CODEX_PATH), and pi is included (same treatment in fullsend-ai#8589,
pinned python3 not Node).

Signed-off-by: James Tanner <jtanner@redhat.com>
jctanner added a commit to jctanner-fullsend-ai/fullsend that referenced this pull request Oct 29, 2026
Renumber the ADR 0150 -> 0152 (0146-0151 are claimed by open PRs
fullsend-ai#8679, fullsend-ai#8694, fullsend-ai#8698, fullsend-ai#8702; fullsend-ai#8702 was filed first for 0150).

Per waynesun09's reviews (first round 14:56, second round 18:29):

- restructure the Decision as rules 1-10 with the conformance table
  separated out (moved to docs/contributing/runtime-implementation.md
  so it can track the implementation as the code changes, linked from
  Consequences)
- add the Options section back per the ADR template
- add rules 9 (executables, not just directories) and 10 (scope)
- gaps tracked in issues only: fullsend-ai#8763 and fullsend-ai#8764 linked bare, no
  implementation-state prose in the ADR
- fold the root-launch case into rule 8 as an explicit scope
  precondition (accurate wording: the PATH still drops relative,
  empty, and missing entries as root; it cannot exclude
  agent-writable directories) instead of a contradictory
  Consequences 'limit'
- cite the pre-fullsend-ai#8605 Codex behavior at the correct SHA
  (bbe0ab2^1 = 191d723), not unqualified line numbers
- state the OpenCode exclusion in rule 6 and the conformance table
  (no ADR 0090 hook wiring until unbound-force#515)
- fix the fullsend-ai#8589 chronology (merged earlier the same day as fullsend-ai#8605,
  not an extension after it)
- fix the Options wording on hash verification (detects a
  substitution only at the next check; the ADR 0094 preflight
  detects at check time, not 'after the fact')
- reference PR fullsend-ai#8261 explicitly as a PR
- fix the architecture.md sentence to state the decision for all
  runtimes, not Codex only
- factual corrections from the first round: the shared resolver is
  hookPreflightInterpreter; the boundary value is FULLSEND_TRUSTED_PATH;
  the pre-fullsend-ai#8605 gap was image-PATH agent-writable dirs; pi included
  (same treatment in fullsend-ai#8589, pinned python3 not Node)
- update the conformance table Codex row to the post-fullsend-ai#8633 mechanism
  (envDataTrustedPin within codexBinaryPin) with the bbe0ab2 state
  noted

Per the dual-model review round (GLM 5.3 + DeepSeek V4.1 Flash):
- breaking change names the runtimes (pi has no version preflight)
- forge scope before Consequences, full forge list

Signed-off-by: James Tanner <jtanner@redhat.com>
jctanner pushed a commit to jctanner-fullsend-ai/fullsend that referenced this pull request Oct 29, 2026
Retroactive record of the decision implemented in PR fullsend-ai#8605 (merged
2026-10-20, merge commit bbe0ab2), with PR fullsend-ai#8589 (pi, merged earlier
the same day) and extended by PR fullsend-ai#8633 (CLI binary pinning, issue
fullsend-ai#8626): hook interpreters and hook PATH resolve only from directories
the agent cannot write; hook settings are runner-held; startup is
fail-closed on all runtimes carrying sandbox tool hooks.

Decision stated as rules 1-10 with a per-runtime conformance table in
docs/contributing/runtime-implementation.md (linked from Consequences
so it tracks the implementation as code changes). Gaps against the
rules are tracked in issues fullsend-ai#8763 and fullsend-ai#8764, both filed by the
reviewer. The root-launch case is folded into rule 8 as an explicit
scope precondition. OpenCode is excluded (no ADR 0090 hook wiring
until unbound-force#515).

Cross-references updated in the same PR per docs/contributing/adrs.md:
ADR 0090 and ADR 0100 implementation notes, architecture.md runtime
contract bullet, and the tool-call risk assessment problem doc (which
previously stated pi hooks stay writable between iterations).

Signed-off-by: James Tanner <jtanner@redhat.com>
jctanner pushed a commit to jctanner-fullsend-ai/fullsend that referenced this pull request Oct 29, 2026
Retroactive record of the decision implemented in PR fullsend-ai#8605 (merged
2026-10-20, merge commit bbe0ab2), with PR fullsend-ai#8589 (pi, merged earlier
the same day) and extended by PR fullsend-ai#8633 (CLI binary pinning, issue
fullsend-ai#8626): hook interpreters and hook PATH resolve only from directories
the agent cannot write; hook settings are runner-held; startup is
fail-closed on all runtimes carrying sandbox tool hooks.

Decision stated as rules 1-10 with a per-runtime conformance table in
docs/contributing/runtime-implementation.md (linked from Consequences
so it tracks the implementation as code changes). Gaps against the
rules are tracked in issues fullsend-ai#8763 and fullsend-ai#8764, both filed by the
reviewer. The root-launch case is folded into rule 8 as an explicit
scope precondition. OpenCode is excluded (no ADR 0090 hook wiring
until unbound-force#515).

Cross-references updated in the same PR per docs/contributing/adrs.md:
ADR 0090 and ADR 0100 implementation notes, architecture.md runtime
contract bullet, and the tool-call risk assessment problem doc (which
previously stated pi hooks stay writable between iterations).

Signed-off-by: James Tanner <jtanner@redhat.com>
jctanner pushed a commit to jctanner-fullsend-ai/fullsend that referenced this pull request Oct 29, 2026
Retroactive record of the decision implemented in PR fullsend-ai#8605 (merged
2026-10-20, merge commit bbe0ab2), with PR fullsend-ai#8589 (pi, merged earlier
the same day) and extended by PR fullsend-ai#8633 (CLI binary pinning, issue
fullsend-ai#8626): hook interpreters and hook PATH resolve only from directories
the agent cannot write; hook settings are runner-held; startup is
fail-closed on all runtimes carrying sandbox tool hooks.

Decision stated as rules 1-10 with a per-runtime conformance table in
docs/contributing/runtime-implementation.md (linked from Consequences
so it tracks the implementation as code changes). Gaps against the
rules are tracked in issues fullsend-ai#8763 and fullsend-ai#8764, both filed by the
reviewer. The root-launch case is folded into rule 8 as an explicit
scope precondition. OpenCode is excluded (no ADR 0090 hook wiring
until unbound-force#515).

Cross-references updated in the same PR per docs/contributing/adrs.md:
ADR 0090 and ADR 0100 implementation notes, architecture.md runtime
contract bullet, and the tool-call risk assessment problem doc (which
previously stated pi hooks stay writable between iterations).

Signed-off-by: James Tanner <jtanner@redhat.com>
jctanner added a commit to jctanner-fullsend-ai/fullsend that referenced this pull request Oct 29, 2026
Retroactive record of the decision implemented in PR fullsend-ai#8605 (merged
2026-10-20, merge commit bbe0ab2), with PR fullsend-ai#8589 (pi, merged earlier
the same day) and extended by PR fullsend-ai#8633 (CLI binary pinning, issue
fullsend-ai#8626): hook interpreters and hook PATH resolve only from directories
the agent cannot write; hook settings are runner-held; startup is
fail-closed on all runtimes carrying sandbox tool hooks.

Decision stated as rules 1-10 with a per-runtime conformance table in
docs/contributing/runtime-implementation.md (linked from Consequences
so it tracks the implementation as code changes). Gaps against the
rules are tracked in issues fullsend-ai#8763 and fullsend-ai#8764, both filed by the
reviewer. The root-launch case is folded into rule 8 as an explicit
scope precondition. OpenCode is excluded (no ADR 0090 hook wiring
until unbound-force#515).

Cross-references updated in the same PR per docs/contributing/adrs.md:
ADR 0090 and ADR 0100 implementation notes, architecture.md runtime
contract bullet, and the tool-call risk assessment problem doc (which
previously stated pi hooks stay writable between iterations).

Signed-off-by: James Tanner <tanner.jc@gmail.com>
jctanner added a commit to jctanner-fullsend-ai/fullsend that referenced this pull request Oct 29, 2026
Retroactive record of the decision implemented in PR fullsend-ai#8605 (merged
2026-10-20, merge commit bbe0ab2), with PR fullsend-ai#8589 (pi, merged earlier
the same day) and extended by PR fullsend-ai#8633 (CLI binary pinning, issue
fullsend-ai#8626): hook interpreters and hook PATH resolve only from directories
the agent cannot write; hook settings are runner-held; startup is
fail-closed on all runtimes carrying sandbox tool hooks.

Decision stated as rules 1-10 with a per-runtime conformance table in
docs/contributing/runtime-implementation.md (linked from Consequences
so it tracks the implementation as code changes). Gaps against the
rules are tracked in issues fullsend-ai#8763 and fullsend-ai#8764, both filed by the
reviewer. The root-launch case is folded into rule 8 as an explicit
scope precondition. OpenCode is excluded (no ADR 0090 hook wiring
until unbound-force#515).

Cross-references updated in the same PR per docs/contributing/adrs.md:
ADR 0090 and ADR 0100 implementation notes, architecture.md runtime
contract bullet, and the tool-call risk assessment problem doc (which
previously stated pi hooks stay writable between iterations).

Signed-off-by: James Tanner <tanner.jc@gmail.com>
jctanner added a commit to jctanner-fullsend-ai/fullsend that referenced this pull request Oct 29, 2026
Retroactive record of the decision implemented in PR fullsend-ai#8605 (merged
2026-10-20, merge commit bbe0ab2), with PR fullsend-ai#8589 (pi, merged earlier
the same day) and extended by PR fullsend-ai#8633 (CLI binary pinning, issue
fullsend-ai#8626): hook interpreters and hook PATH resolve only from directories
the agent cannot write; hook settings are runner-held; startup is
fail-closed on all runtimes carrying sandbox tool hooks.

Decision stated as rules 1-10 with a per-runtime conformance table in
docs/contributing/runtime-implementation.md (linked from Consequences
so it tracks the implementation as code changes). Gaps against the
rules are tracked in issues fullsend-ai#8763 and fullsend-ai#8764, both filed by the
reviewer. The root-launch case is folded into rule 8 as an explicit
scope precondition. OpenCode is excluded (no ADR 0090 hook wiring
until unbound-force#515).

Cross-references updated in the same PR per docs/contributing/adrs.md:
ADR 0090 and ADR 0100 implementation notes, architecture.md runtime
contract bullet, and the tool-call risk assessment problem doc (which
previously stated pi hooks stay writable between iterations).

Signed-off-by: James Tanner <tanner.jc@gmail.com>
jctanner added a commit to jctanner-fullsend-ai/fullsend that referenced this pull request Oct 29, 2026
Retroactive record of the decision implemented in PR fullsend-ai#8605 (merged
2026-10-20, merge commit bbe0ab2), with PR fullsend-ai#8589 (pi, merged earlier
the same day) and extended by PR fullsend-ai#8633 (CLI binary pinning, issue
fullsend-ai#8626): hook interpreters and hook PATH resolve only from directories
the agent cannot write; hook settings are runner-held; startup is
fail-closed on all runtimes carrying sandbox tool hooks.

Decision stated as rules 1-10 with a per-runtime conformance table in
docs/contributing/runtime-implementation.md (linked from Consequences
so it tracks the implementation as code changes). Gaps against the
rules are tracked in issues fullsend-ai#8763 and fullsend-ai#8764, both filed by the
reviewer. The root-launch case is folded into rule 8 as an explicit
scope precondition. OpenCode is excluded (no ADR 0090 hook wiring
until unbound-force#515).

Cross-references updated in the same PR per docs/contributing/adrs.md:
ADR 0090 and ADR 0100 implementation notes, architecture.md runtime
contract bullet, and the tool-call risk assessment problem doc (which
previously stated pi hooks stay writable between iterations).

Signed-off-by: James Tanner <tanner.jc@gmail.com>

This branch was successfully deployed

1 active and 1 inactive deployments
site-preview — 50ef6254 Deployed Oct 20, 2026 by github-actions[bot]
dev — 50ef6254 Deployed Oct 20, 2026 by waynesun09 via behaviour #17398
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

component/sandbox OpenShell sandbox environment fullsend-no-fix Skip bot-triggered fix agent runs go Pull requests that update go code ready-for-merge All reviewers approved — ready to merge ready-for-review Triggers review agent dispatch risk/moderate PR risk: moderate security Security threat model and related concerns

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Pin the CLI binaries and their node interpreter on the trusted PATH

1 participant