Skip to content

fix(#8577): run pi hook scripts with the python3 pinned before .env - #8589

Merged
waynesun09 merged 3 commits into
mainfrom
agent/8577-pin-pi-hook-python
Oct 20, 2026
Merged

waynesun09 merged 3 commits into
mainfrom
agent/8577-pin-pi-hook-python

Conversation

@fullsend-ai-coder

@fullsend-ai-coder fullsend-ai-coder Bot commented Oct 19, 2026 •

Copy link
Copy Markdown
Contributor

Summary

pi's hook adapter (fullsend-hooks.js, runScript) started each hook script with a bare python3, looked up on the PATH left after the agent-writable .env was loaded. A python3 stub that exits 0 placed earlier on that PATH made every hook read as allowed without its script running. The adapter now runs the absolute python3 the launch pins before .env is read, and blocks the call if that pin is missing.

Related Issue

#8577 (follow-up to #8498 / #8565)

Changes

  • internal/runtime/pi_run.go: after envDataLoad, export the loader's pre-.env pin as FULLSEND_PI_HOOK_PYTHON="$FULLSEND_ENV_PYTHON", and add FULLSEND_PI_HOOK_PYTHON to the loader's drop list for the pi launch, so .env can neither set nor clear it. Sub-agents inherit it through the env the Agent extension passes to children (childEnv). Plugin env cannot set it either, because FULLSEND_* is a reserved prefix.
  • internal/runtime/pi_extension/fullsend-hooks.js: runScript spawns the interpreter from FULLSEND_PI_HOOK_PYTHON. If the value is missing, empty or not absolute, the call is blocked and nothing is spawned (fail closed). env is injectable through runScript/createHooks for tests.
  • Hook PATH: the launch also exports the trusted PATH recorded before .env (fix(#8575)!: harden and tidy the .env-as-data launch loader #8591) as FULLSEND_PI_HOOK_PATH (dropped from .env like the interpreter pin), and runScript runs each hook as python3 -E -s -B <script> with that PATH. A missing, empty or non-absolute value blocks the call without spawning.
  • docs/contributing/runtime-implementation.md: the pi hook adapter contract now describes the pinned interpreter.
  • Codex: checked, no change. hooks.json names an absolute interpreter resolved at Bootstrap (codexPreflightPython), the wiring digest covers it, and the launch restores the pre-.env PATH before codex starts.

Testing

  • node --test internal/runtime/pi_extension/fullsend-hooks.test.mjs: new tests cover:
    • a real python3 stub first on PATH is never spawned, and a blocking hook's verdict is honoured
    • spawn uses the pinned path
    • unset, empty, python3 and bin/python3 values block without spawning
    • tool_call and tool_result both fail closed without a pin
  • go test ./internal/runtime/: TestBuildPiRunCommand_HookPythonPinned checks the name is dropped by the loader and exported after the .env load, before pi starts. TestPiHookPythonExport_IgnoresEnv runs the real loader with a .env that sets the name and prepends a python3 stub to PATH. The exported value stays the pre-.env interpreter.
  • Rebased onto main after fix(#8575)!: harden and tidy the .env-as-data launch loader #8591: go test ./internal/runtime/... ./internal/security/... ./internal/cli/... pass as a non-root user on Linux (dash /bin/sh); node --test on the pi extension: 140 pass, 4 skipped.
  • Patch coverage: piHookPythonExport and buildPiRunCommand are at 100%.
  • Hooks: pre-commit itself could not fetch hook repositories in the sandbox (TLS failure), so the applicable hooks were run directly and all passed: pre-commit-hooks 6.0.0 file checks, gofmt, go vet, scan-secrets, lint-broken-symlinks, lint-docs-links and lychee.
  • Two tests also fail on main in this sandbox and are unrelated to this change: TestBuildRunCommand_ClaudeMissingExits127 (a real claude binary is on PATH) and one fullsend-agent.test.mjs process-group kill test.

Checklist

  • PR title follows Conventional Commits (correct type, ! for breaking changes)
  • Commits are not signed off: autonomous agent commit, exempt from DCO

🤖 Generated with Claude Code


Closes #8577

Post-script verification

  • Branch is not main/master (agent/8577-pin-pi-hook-python)
  • Secret scan passed (gitleaks — 5fc4c47a1d40c2ab0a748e3bd2f7b9f8a697ca50..HEAD)
  • PR body secret scan passed (gitleaks — no-git)

@fullsend-ai-review

fullsend-ai-review Bot commented Oct 19, 2026 •

Copy link
Copy Markdown

🤖 Finished Review · ✅ Success · Started 9:35 PM UTC · Completed 9:44 PM UTC

Commit: 6bba3a0 · View workflow run →

Runtime: pi · Model: sonnet → claude-sonnet-5-5 · Effort: high · Cost: $2.55

@github-actions

github-actions Bot commented Oct 19, 2026 •

Copy link
Copy Markdown

Site preview

Preview: https://00dc6a6a-site.fullsend-ai.workers.dev

Commit: 3de4f32870325f33f0e137e6c86d625b29d72552

@fullsend-ai-review fullsend-ai-review Bot added the risk/moderate PR risk: moderate label Oct 19, 2026
@fullsend-ai-review

fullsend-ai-review Bot commented Oct 19, 2026 •

Copy link
Copy Markdown

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

Details

Compact 6-file security hardening PR by a bot with 50% test coverage and aligned issue scope, evaluated at moderate risk due to active runtime churn and modifying existing behavior without a feature flag.

Previous run

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

Details

Compact 6-file security hardening PR by a bot with 50% test coverage and aligned issue scope, evaluated at moderate risk due to active runtime churn and modifying existing behavior without a feature flag.

Previous run (2)

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

Details

Compact 6-file security hardening PR by a bot with 50% test coverage and aligned issue scope, evaluated at moderate risk due to active runtime churn and modifying existing behavior without a feature flag.

Previous run (3)

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

Details

Compact 6-file security hardening PR by a bot with 50% test coverage and clear issue alignment, yielding moderate risk due to active runtime history and modifying existing behavior without a feature flag.

@fullsend-ai-review

fullsend-ai-review Bot commented Oct 19, 2026 •

Copy link
Copy Markdown

Looks good to me

Previous run

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

Looks good to me

Previous run (2)

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

Looks good to me

Earlier findings

  • f_e640e713fb06c1f6 — resolved_by_change: the doc comment for TestBuildPiRunCommand_HookPythonPinned is now its own, and the ManifestGuard comment sits above its function.
  • f_529c2aefb5455ac0 — resolved_by_change: the TestPiHookPythonExport_IgnoresEnv doc comment now starts with the function name.
Previous run (3)

<!-- fullsend:review-findings-v2:eyJ2ZXJzaW9uIjoyLCJhY3Rpb24iOiJyZXF1ZXN0LWNoYW5nZXMiLCJmaW5kaW5ncyI6W3sic2V2ZXJpdHkiOiJsb3ciLCJjYXRlZ29yeSI6ImRvYy1zdHlsZSIsImZpbGUiOiJpbnRlcm5hbC9ydW50aW1lL3BpX3J1bl90ZXN0LmdvIiwiaWQiOiJmX2U2NDBlNzEzZmIwNmMxZjYiLCJsaW5lIjozNjcsImFjdGlvbmFibGUiOnRydWV9LHsic2V2ZXJpdHkiOiJsb3ciLCJjYXRlZ29yeSI6ImRvYy1zdHlsZSIsImZpbGUiOiJpbnRlcm5hbC9ydW50aW1lL3BpX3J1bl90ZXN0LmdvIiwiaWQiOiJmXzUyOWMyYWVmYjU0NTVhYzAiLCJsaW5lIjozODYsImFjdGlvbmFibGUiOmZhbHNlfV19 -->

Review

Findings

Low

  • [doc-style] internal/runtime/pi_run_test.go:367 — The doc comment for TestBuildPiRunCommand_ManifestGuard (lines 367-369) now sits above TestBuildPiRunCommand_HookPythonPinned. The new tests were inserted between that comment and its function. As a result TestBuildPiRunCommand_ManifestGuard (line 410) has no doc comment, and TestBuildPiRunCommand_HookPythonPinned (line 372) carries a misleading one.
    Remediation: Move the TestBuildPiRunCommand_ManifestGuard comment back to directly above func TestBuildPiRunCommand_ManifestGuard (line 410). Give TestBuildPiRunCommand_HookPythonPinned its own comment that starts with its name.

  • [doc-style] internal/runtime/pi_run_test.go:386 — The doc comment for TestPiHookPythonExport_IgnoresEnv starts with "The exported value is..." rather than the function name. The other test doc comments in this file start with the function name.
    Remediation: Start the comment with TestPiHookPythonExport_IgnoresEnv. This is a minor nit and is not blocking.


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.

@codecov

codecov Bot commented Oct 19, 2026

Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

@fullsend-ai-coder

fullsend-ai-coder Bot commented Oct 19, 2026 •

Copy link
Copy Markdown
Contributor Author

🤖 Finished Fix · ✅ Success · Started 9:46 PM UTC · Completed 9:52 PM UTC

Commit: 6bba3a0 · View workflow run →

Runtime: claude · Model: sonnet → claude-sonnet-5-5 · Effort: high · Cost: $0.32

fullsend-ai-coder Bot added a commit that referenced this pull request Oct 19, 2026
Move the TestBuildPiRunCommand_ManifestGuard doc comment back above its
function, and give TestBuildPiRunCommand_HookPythonPinned and
TestPiHookPythonExport_IgnoresEnv doc comments that start with their names.

Note: pre-commit could not fetch hook repositories (TLS verification failure
in the sandbox); gofmt and go vet were run directly instead. go test
./internal/runtime fails only TestBuildRunCommand_ClaudeMissingExits127, which
also fails without this change (a claude binary exists on the sandbox PATH).

Addresses #8589

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

Copy link
Copy Markdown
Contributor Author

🔧 Fix agent — iteration 1 (bot-triggered)

Addressed both low-severity doc-comment findings in pi_run_test.go (comment-only change). pre-commit could not fetch hooks in the sandbox (TLS error), so gofmt and go vet were run directly. go test for internal/runtime passes except TestBuildRunCommand_ClaudeMissingExits127, which fails identically without this change because a claude binary is on the sandbox PATH.

Fixed (2):

  1. Doc comment for TestBuildPiRunCommand_ManifestGuard was displaced above TestBuildPiRunCommand_HookPythonPinned, leaving the former undocumented and the latter misdocumented (internal/runtime/pi_run_test.go): Moved the ManifestGuard comment back directly above its function and gave HookPythonPinned its own comment starting with its name.
  2. Doc comment for TestPiHookPythonExport_IgnoresEnv did not start with the function name (internal/runtime/pi_run_test.go): Reworded the comment so it begins with TestPiHookPythonExport_IgnoresEnv, matching the other test comments in the file.

Tests: passed

CI inspections (7):

  1. CI / test (passing, success): Passed on the reviewed head.
  2. CI / test-sandbox-darwin (passing, success): Passed on the reviewed head.
  3. CI / web (passing, success): Passed on the reviewed head.
  4. CI / commit-lint (passing, success): Passed on the reviewed head.
  5. E2E Tests / playback (pending, in_progress): Still running at inspection time; no failure observed.
  6. E2E Tests / behaviour (pending, in_progress): Still running at inspection time; no failure observed.
  7. codecov/patch (passing, success): Patch coverage check passed.

Conflict update: skipped; strategy none; forge MERGEABLE; target main

Next steps:

  • /fs-review — request a re-review of the changes
  • /fs-fix <your instruction> — run another fix pass with specific guidance
  • Push commits directly — review re-runs automatically on push
    Updated by fullsend fix agent

@fullsend-ai-review

fullsend-ai-review Bot commented Oct 19, 2026 •

Copy link
Copy Markdown

🤖 Finished Review · ✅ Success · Started 9:54 PM UTC · Completed 9:58 PM UTC

Commit: 47c18f0 · View workflow run →

Runtime: pi · Model: sonnet → claude-sonnet-5-5 · Effort: high · Cost: $0.92

fullsend-ai-review[bot]

This comment was marked as outdated.

@fullsend-ai-review fullsend-ai-review Bot added the ready-for-merge All reviewers approved — ready to merge label Oct 19, 2026
@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 19, 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.

waynesun09 pushed a commit that referenced this pull request Oct 20, 2026
Move the TestBuildPiRunCommand_ManifestGuard doc comment back above its
function, and give TestBuildPiRunCommand_HookPythonPinned and
TestPiHookPythonExport_IgnoresEnv doc comments that start with their names.

Note: pre-commit could not fetch hook repositories (TLS verification failure
in the sandbox); gofmt and go vet were run directly instead. go test
./internal/runtime fails only TestBuildRunCommand_ClaudeMissingExits127, which
also fails without this change (a claude binary exists on the sandbox PATH).

Addresses #8589

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
@waynesun09
waynesun09 force-pushed the agent/8577-pin-pi-hook-python branch from 47c18f0 to 61d4229 Compare October 20, 2026 05:57
@fullsend-ai-review

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

Copy link
Copy Markdown

🤖 Finished Review · ✅ Success · Started 9:46 AM UTC · Completed 9:57 AM UTC

Commit: 3de4f32 · View workflow run →

Runtime: pi · Model: sonnet → claude-sonnet-5-5 · Effort: high · Cost: $2.84

@fullsend-ai-review
fullsend-ai-review Bot dismissed their stale review October 20, 2026 09:56

Superseded by updated review

@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
@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
@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
@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 c299191 Oct 20, 2026
31 checks passed
@waynesun09
waynesun09 deleted the agent/8577-pin-pi-hook-python branch October 20, 2026 12:55
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 (fail-open with
  warning, per-runtime resolvers, version-floor acceptance,
  hash-verification as primary mechanism — each rejected)
- add rules 9 (executables, not just directories) and 10 (scope:
  settings sources fullsend-ai#8637, hooks.json integrity fullsend-ai#8261, plugin trust
  ADR 0094)
- gaps against the rules are tracked in issues, not the ADR: fullsend-ai#8763
  (per-file trust for every executable a hook runs) and fullsend-ai#8764 (paths
  that let a tool call through without a hook verdict), both filed by
  the reviewer; rule 8's root-launch exception stays as a one-sentence
  stated limit
- fix the pre-fullsend-ai#8605 Codex wording: the PATH was restored for itself
  and its hook adapter's children
- 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)

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 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 — 3de4f328 Deployed Oct 20, 2026 by github-actions[bot]
dev — 3de4f328 Deployed Oct 20, 2026 by waynesun09 via behaviour #17294
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

fullsend-no-fix Skip bot-triggered fix agent runs ready-for-merge All reviewers approved — ready to merge ready-for-review Triggers review agent dispatch risk/moderate PR risk: moderate

Projects

None yet

Development

Successfully merging this pull request may close these issues.

pi hook adapter resolves python3 through the agent-influenced PATH

1 participant